© 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. 1737
    Prev
    Next
    INDEX
    Explanations

    instances where someone is declining to comment on a particular matter

    oai_token-act-pair · gpt-3.5-turbo

    instances where entities are declining to comment on various matters

    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
    externalActionCode
    -0.84
    TY
    -0.76
    reference
    -0.76
    YE
    -0.74
    ARM
    -0.73
    ©¶æ¥µ
    -0.69
    ennes
    -0.67
    MODE
    -0.66
    MAP
    -0.65
    ACT
    -0.63
    POSITIVE LOGITS
     behalf
    1.62
    erous
    0.98
     matters
    0.96
     occasion
    0.90
    shore
    0.88
     topics
    0.87
    eness
    0.84
     whether
    0.84
     how
    0.83
    etime
    0.80
    Activations Density 0.118%

    No Known Activations