© 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. 17124
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of taking actions or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions used to connect ideas or actions

    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
    meet
    -0.79
    ieth
    -0.74
    ANC
    -0.74
    ente
    -0.72
    expr
    -0.71
    udo
    -0.70
    DEN
    -0.70
    existence
    -0.69
    ibl
    -0.69
    iors
    -0.69
    POSITIVE LOGITS
     then
    1.06
     THEN
    1.02
     proceeded
    0.97
     toss
    0.91
     shove
    0.91
     threw
    0.89
     put
    0.89
     thence
    0.88
     tossed
    0.86
     vo
    0.86
    Activations Density 0.307%

    No Known Activations