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

    Neuronpedia

    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. 4118
    Prev
    Next
    INDEX
    Explanations

    names of a specific person, "Steve"

    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
    1581
    +0.16
    0.7%
    687
    +0.13
    0.5%
    866
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1581
    +0.16
    0.02
    687
    +0.13
    0.02
    874
    +0.12
    0.02
    Negative Logits
     unspeak
    -1.21
     cushi
    -1.06
     indescri
    -1.02
     impelled
    -1.01
     shenan
    -0.99
     impra
    -0.98
     maneu
    -0.91
     tolerably
    -0.91
     hairc
    -0.91
     apprehen
    -0.90
    POSITIVE LOGITS
     Steve
    1.42
    Steve
    1.38
    STEVE
    1.22
     kosme
    1.01
    steve
    0.99
     utop
    0.99
     notor
    0.97
     steve
    0.95
     alkoh
    0.95
     Kategor
    0.95
    Activations Density 0.055%

    No Known Activations