© 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. 6392
    Prev
    Next
    INDEX
    Explanations

    numbers at the beginning of sentences and the symbol ':' in a text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting symbols, particularly colons

    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
    etheless
    -0.71
     disliked
    -0.71
     referees
    -0.69
     receipt
    -0.66
    ibur
    -0.65
     evapor
    -0.65
     brewed
    -0.63
     stagn
    -0.63
     pads
    -0.62
     diver
    -0.62
    POSITIVE LOGITS
     Exactly
    0.93
     Tonight
    0.86
     Yeah
    0.82
     Well
    0.80
    Correct
    0.78
     Wow
    0.76
     Alright
    0.75
     Explain
    0.75
    Yeah
    0.74
    Thirty
    0.74
    Activations Density 0.043%

    No Known Activations