© 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. 1707
    Prev
    Next
    INDEX
    Explanations

    terms related to progressive social or technological advancements

    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
    1233
    +0.08
    0.3%
    1994
    +0.08
    0.3%
    871
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    697
    +0.08
    0.03
    1233
    +0.08
    0.03
    726
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.41
    public
    -0.84
    ,
    -0.76
     in
    -0.74
     at
    -0.74
    </
    -0.73
     put
    -0.73
    put
    -0.72
    ↵↵
    -0.72
    int
    -0.72
    POSITIVE LOGITS
     progressive
    2.51
     ftu
    2.43
     Progres
    2.41
     Progressive
    2.39
    Progressive
    2.37
     fta
    2.36
    progressive
    2.25
     ftre
    2.18
     maneu
    2.17
     aen
    2.17
    Activations Density 0.153%

    No Known Activations