© 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. 7-RES-JB
    11. 4050
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to decision-making, locations, and team dynamics

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and institutional structures

    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
    ahan
    -0.59
    roxy
    -0.57
    BuyableInstoreAndOnline
    -0.56
     upgr
    -0.55
     certific
    -0.54
     largeDownload
    -0.53
     roundup
    -0.53
     Mush
    -0.53
     supervised
    -0.52
     oxid
    -0.51
    POSITIVE LOGITS
    worthiness
    0.97
     beforehand
    0.91
     differently
    0.89
    vantage
    0.75
     accurately
    0.74
     correctly
    0.71
     patterns
    0.69
    olicy
    0.67
    igraph
    0.66
     BEFORE
    0.65
    Activations Density 0.856%

    No Known Activations