© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11137
    Prev
    Next
    INDEX
    Explanations

    sequences related to speaking or talking

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the verb "speak" (and its conjugated/gerund forms such as speaks, speaking).

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    538
    +0.13
    0.4%
    1096
    +0.12
    0.4%
    1964
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    538
    +0.13
    0.05
    47
    +0.12
    0.04
    1964
    +0.12
    0.04
    Negative Logits
     kriminal
    -0.64
     kooper
    -0.59
     mikrofon
    -0.59
     akut
    -0.59
     Hül
    -0.56
     kosme
    -0.56
     silikon
    -0.56
     minimalis
    -0.56
     laboratorium
    -0.55
     Strukt
    -0.55
    POSITIVE LOGITS
     speak
    1.11
     speaking
    1.07
     spoke
    1.04
     spoken
    1.01
     Speak
    1.01
     speaks
    1.01
    speak
    0.93
     Speaking
    0.92
    Speak
    0.91
    spoke
    0.88
    Activations Density 0.097%

    No Known Activations