Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 6966
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to decisions or actions involving a choice between two possibilities

    oai_token-act-pair · gpt-3.5-turbo

    components and aspects related to constructed identities or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chambers
    -0.77
    Ĥª
    -0.68
     Doors
    -0.68
    Ń·
    -0.66
     prayer
    -0.60
     prayers
    -0.60
    APTER
    -0.57
     Gillespie
    -0.57
     throats
    -0.56
     coax
    -0.56
    POSITIVE LOGITS
    your
    0.89
    export
    0.81
    up
    0.78
    time
    0.76
    react
    0.76
    luster
    0.75
    advertisement
    0.75
    ins
    0.74
    chart
    0.74
    existing
    0.73
    Activations Density 0.071%

    No Known Activations