© 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. 22676
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing probability or likelihood

    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
    gado
    -0.75
    inth
    -0.74
    enstein
    -0.73
    aredevil
    -0.73
    osi
    -0.71
    zeb
    -0.70
    artney
    -0.70
    issy
    -0.70
    leck
    -0.69
    neys
    -0.69
    POSITIVE LOGITS
     underest
    0.88
     underestimated
    0.74
    won
    0.74
     overest
    0.73
     underestimate
    0.72
     culprit
    0.72
     doomed
    0.70
     linem
    0.70
     exagger
    0.69
     someday
    0.68
    Activations Density 0.047%

    No Known Activations