© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2224
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and procedural information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.4%
    198
    +0.05
    0.2%
    618
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.10
    0.13
    1499
    +0.05
    0.13
    198
    +0.04
    0.09
    Negative Logits
    <bos>
    -1.79
    .
    -0.96
    <eos>
    -0.87
    ,
    -0.87
    !
    -0.86
    public
    -0.82
    //
    -0.82
    }{||
    -0.82
    ?
    -0.81
     also
    -0.79
    POSITIVE LOGITS
     fta
    2.54
     effe
    2.50
     aen
    2.48
     wien
    2.46
     ftu
    2.42
     fte
    2.42
     stockholm
    2.40
     emphat
    2.38
     affor
    2.32
     nece
    2.32
    Activations Density 1.484%

    No Known Activations