© 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. 8-RES-JB
    11. 6931
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rave
    -0.71
    wagon
    -0.69
     seriousness
    -0.60
    ADVERTISEMENT
    -0.60
    tsy
    -0.59
     trillion
    -0.57
     Growth
    -0.56
    Station
    -0.55
    orde
    -0.54
    take
    -0.54
    POSITIVE LOGITS
    ynchron
    0.74
    é¾įåĸļ士
    0.70
    azo
    0.67
    orah
    0.65
    undo
    0.65
    ado
    0.63
    velt
    0.62
    erson
    0.62
     dynamically
    0.62
    ociated
    0.61
    Activations Density 0.058%

    No Known Activations