© 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. 6377
    Prev
    Next
    INDEX
    Explanations

    superlatives that imply a sense of extreme or topmost quality or degree

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "highest"

    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
    md
    -0.73
    izon
    -0.73
    vous
    -0.71
    neys
    -0.68
    rahim
    -0.68
    skirts
    -0.67
    illard
    -0.65
    chini
    -0.65
    agra
    -0.65
    nikov
    -0.64
    POSITIVE LOGITS
     bidder
    1.04
     rated
    0.95
     earners
    0.84
     level
    0.84
     priority
    0.83
     pinnacle
    0.82
     concentrations
    0.81
     imaginable
    0.80
     tier
    0.80
     possible
    0.80
    Activations Density 0.021%

    No Known Activations