© 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. 3402
    Prev
    Next
    INDEX
    Explanations

    words related to personal interactions and decision-making

    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
    674
    +0.09
    0.2%
    69
    +0.07
    0.2%
    934
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.09
    0.04
    787
    +0.07
    0.03
    1031
    +0.07
    0.04
    Negative Logits
     increa
    -1.61
     unve
    -1.56
     reluct
    -1.56
     maneu
    -1.54
     unlaw
    -1.51
     suscep
    -1.47
     affor
    -1.47
     encomp
    -1.46
     impra
    -1.46
     fortn
    -1.45
    POSITIVE LOGITS
    <bos>
    1.24
     available
    0.83
     best
    0.82
    best
    0.75
    available
    0.73
    contentLoaded
    0.73
    hichever
    0.70
     whichever
    0.68
     easiest
    0.68
     whatever
    0.67
    Activations Density 0.344%

    No Known Activations