© 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. 1-RES-JB
    11. 3093
    Prev
    Next
    INDEX
    Explanations

    German words

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with intelligence or cleverness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restrooms
    -0.67
    culus
    -0.67
     genital
    -0.66
    electric
    -0.64
    healthy
    -0.64
    inventory
    -0.63
    MN
    -0.62
     Cats
    -0.61
    alg
    -0.61
    culated
    -0.61
    POSITIVE LOGITS
    icht
    1.17
    entimes
    1.13
    iness
    0.86
    nown
    0.82
    rag
    0.80
    linger
    0.78
    lich
    0.77
    mann
    0.76
    wald
    0.76
    ueller
    0.74
    Activations Density 0.007%

    No Known Activations