© 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. 4-RES-JB
    11. 15349
    Prev
    Next
    INDEX
    Explanations

    phrases related to situations of excessive intensity or quantity

    oai_token-act-pair · gpt-3.5-turbo

    the word "excessive" and its variations

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

    No Comments

    Negative Logits
    Reviewed
    -0.82
    hran
    -0.81
    udder
    -0.74
    bard
    -0.74
    rol
    -0.73
    ect
    -0.72
    stone
    -0.72
    HCR
    -0.69
    stones
    -0.69
    finder
    -0.69
    POSITIVE LOGITS
     amounts
    0.97
     excessive
    0.96
     punishment
    0.94
     amount
    0.83
     accumulation
    0.82
     indul
    0.79
     expenditure
    0.78
     provocation
    0.77
     consumption
    0.77
     capacity
    0.75
    Activations Density 0.016%

    No Known Activations