© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    the word "unto"

    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
    930
    +0.07
    0.2%
    920
    +0.07
    0.2%
    850
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.07
    0.02
    850
    +0.07
    0.02
    461
    +0.07
    0.02
    Negative Logits
    public
    -0.81
    core
    -0.77
    beta
    -0.71
    ">//
    -0.71
    Referencias
    -0.71
    地方
    -0.71
    protected
    -0.70
    多
    -0.70
    pos
    -0.70
    ba
    -0.69
    POSITIVE LOGITS
     unto
    2.88
     Unto
    2.82
     shenan
    2.59
     maneu
    2.53
     milf
    2.52
     affor
    2.44
     accla
    2.41
     wikihow
    2.36
     increa
    2.31
     reluct
    2.30
    Activations Density 0.218%

    No Known Activations