© 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. 4073
    Prev
    Next
    INDEX
    Explanations

    technical terms, possibly related to information technology

    oai_token-act-pair · gpt-3.5-turbo

    words related to origin and classification

    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
     Sunshine
    -0.54
     Hyde
    -0.53
     Settlement
    -0.52
     Sutherland
    -0.52
     distraction
    -0.50
     Hurt
    -0.48
     Semin
    -0.48
     Trojan
    -0.47
     Violence
    -0.47
     Franks
    -0.46
    POSITIVE LOGITS
    ishly
    0.92
    ifully
    0.92
    arily
    0.92
    ially
    0.86
    cially
    0.81
    pecially
    0.80
    atively
    0.80
    atically
    0.80
    ically
    0.80
    wise
    0.80
    Activations Density 0.733%

    No Known Activations