© 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. 1557
    Prev
    Next
    INDEX
    Explanations

    references to psychological terms and behaviors

    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
    1677
    +0.08
    0.2%
    687
    +0.07
    0.2%
    1059
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.04
    690
    +0.07
    0.04
    1120
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.12
    HasOne
    -0.60
    Více
    -0.58
    Aceptar
    -0.55
    public
    -0.54
     pray
    -0.54
    cuál
    -0.54
    Além
    -0.53
    ะ
    -0.53
     maintain
    -0.53
    POSITIVE LOGITS
     fta
    1.47
     „,
    1.46
     fte
    1.43
     ftu
    1.42
     fep
    1.38
     Sén
    1.36
     fto
    1.35
     wien
    1.34
     foon
    1.33
     myn
    1.33
    Activations Density 0.293%

    No Known Activations