© 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. 10-RES-JB
    11. 17278
    Prev
    Next
    INDEX
    Explanations

    phrases conveying uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opian
    -0.65
     Statement
    -0.56
     Flavoring
    -0.54
     Derby
    -0.54
    Þ
    -0.54
     Mash
    -0.53
     Crossing
    -0.52
     Hitch
    -0.52
    ĸļ
    -0.51
     Citation
    -0.51
    POSITIVE LOGITS
    Not
    0.85
    not
    0.84
    't
    0.81
     not
    0.75
    erent
    0.71
     Not
    0.67
    hap
    0.63
    BE
    0.63
    abouts
    0.63
    itely
    0.63
    Activations Density 0.034%

    No Known Activations