© 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. 1227
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing disappointment or dissatisfaction

    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
    +0.12
    0.6%
    1919
    +0.06
    0.3%
    1675
    +0.05
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.12
    0.17
    1675
    +0.06
    0.15
    1993
    +0.05
    0.10
    Negative Logits
    <bos>
    -1.86
    public
    -0.90
    .
    -0.88
    ,
    -0.85
    //
    -0.82
    void
    -0.82
     in
    -0.80
    ↵↵
    -0.80
     to
    -0.77
     of
    -0.76
    POSITIVE LOGITS
     affor
    2.69
     maneu
    2.61
     increa
    2.60
     impra
    2.41
     volunte
    2.38
     disagre
    2.37
     inev
    2.36
     excru
    2.35
     accla
    2.35
     strick
    2.34
    Activations Density 1.700%

    No Known Activations