© 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. 18515
    Prev
    Next
    INDEX
    Explanations

    people or situations that someone might be interested in

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to interest or enthusiasm about topics or activities

    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
    Fail
    -0.71
     stacked
    -0.69
    ework
    -0.61
    ania
    -0.60
     fabricated
    -0.59
     botched
    -0.58
    hemy
    -0.58
     Saints
    -0.56
     survived
    -0.56
     deteriorated
    -0.54
    POSITIVE LOGITS
    hook
    0.69
    nels
    0.68
    ãĥĦ
    0.68
     enough
    0.67
    ately
    0.66
    encing
    0.66
    tion
    0.66
    edIn
    0.66
    iotics
    0.66
    iments
    0.66
    Activations Density 0.023%

    No Known Activations