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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12953
    Prev
    Next
    INDEX
    Explanations

    phrases related to the middle of events or people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    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
    680
    +0.17
    0.6%
    897
    +0.13
    0.5%
    765
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.17
    0.04
    765
    +0.13
    0.04
    1861
    +0.13
    0.04
    Negative Logits
    paddingVertical
    -0.48
     NUKAT
    -0.47
     óra
    -0.47
     reflectance
    -0.45
    ,:]
    -0.45
    authToken
    -0.43
    notag
    -0.43
     március
    -0.42
     egyszer
    -0.42
    MatButtonModule
    -0.42
    POSITIVE LOGITS
    Middle
    1.27
     Middle
    1.25
     middle
    1.21
    middle
    1.20
     MIDDLE
    1.19
    MIDDLE
    1.07
     Middles
    0.96
     Middel
    0.84
     Middleton
    0.81
     relève
    0.75
    Activations Density 0.066%

    No Known Activations