© 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. 2478
    Prev
    Next
    INDEX
    Explanations

    terms related to the folk genre of music

    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
    1506
    +0.09
    0.3%
    437
    +0.08
    0.3%
    331
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1506
    +0.09
    0.02
    437
    +0.08
    0.02
    868
    +0.08
    0.02
    Negative Logits
    public
    -0.74
    <bos>
    -0.73
    ContentAlignment
    -0.72
    void
    -0.70
    char
    -0.67
    djangoproject
    -0.67
    ടു
    -0.67
    HasColumnType
    -0.65
    def
    -0.64
    마
    -0.64
    POSITIVE LOGITS
     folk
    2.64
     Folk
    2.52
    Folk
    2.28
    folk
    2.11
     affor
    1.88
     maneu
    1.81
     excru
    1.79
     emphat
    1.75
     reluct
    1.75
     increa
    1.73
    Activations Density 0.179%

    No Known Activations