© 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. 7-RES-JB
    11. 23438
    Prev
    Next
    INDEX
    Explanations

    words indicating that something is too extreme, intense, or unsuitable in some way

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate something is "too" or beyond a certain threshold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qi
    -0.76
     Accessed
    -0.74
    LM
    -0.73
    ipple
    -0.72
    deen
    -0.71
    provided
    -0.71
    nex
    -0.70
    loo
    -0.70
    doi
    -0.70
    chenko
    -0.69
    POSITIVE LOGITS
    geries
    0.96
     experimentation
    0.87
     comparison
    0.83
     purposes
    0.79
     us
    0.77
     sustained
    0.76
    gery
    0.75
     comparisons
    0.73
     inclusion
    0.73
     optimum
    0.71
    Activations Density 0.152%

    No Known Activations