© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 20917
    Prev
    Next
    INDEX
    Explanations

    words related to actions or qualities related to a person or group

    oai_token-act-pair · gpt-3.5-turbo

    words associated with cooperation, social dynamics, and influence

    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
     Guan
    -0.71
    htaking
    -0.68
    anton
    -0.67
    ©¶æ
    -0.65
     himself
    -0.63
    hander
    -0.61
     Himself
    -0.60
    cussion
    -0.60
     extrad
    -0.59
     Brady
    -0.59
    POSITIVE LOGITS
     selves
    1.58
     counterparts
    1.38
     brethren
    0.94
    selves
    0.88
     asses
    0.86
     careers
    0.81
     tongues
    0.78
     identities
    0.77
     histories
    0.77
     equivalents
    0.75
    Activations Density 0.474%

    No Known Activations