© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 2596
    Prev
    Next
    INDEX
    Explanations

    text indicating to look at or refer to information below for additional details or context

    oai_token-act-pair · gpt-3.5-turbo

    references to supplementary materials or sections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imperson
    -0.73
    urated
    -0.69
    owered
    -0.66
    ococ
    -0.66
    geries
    -0.64
     Haram
    -0.64
    rained
    -0.62
     transpl
    -0.61
     awoke
    -0.59
     pretended
    -0.58
    POSITIVE LOGITS
     below
    0.98
    below
    0.96
    >.
    0.95
    autions
    0.95
     ).
    0.93
    ]).
    0.92
     appendix
    0.91
    )).
    0.88
     section
    0.87
    endix
    0.86
    Activations Density 0.160%

    No Known Activations