© 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. 4857
    Prev
    Next
    INDEX
    Explanations

    medical conditions, specifically related to the digestive system and prostate

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cancer and anatomical references

    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
    ombie
    -0.76
    arettes
    -0.73
    aneers
    -0.73
     Ãľ
    -0.68
    emo
    -0.66
    hou
    -0.66
    abwe
    -0.64
    sung
    -0.64
     Lies
    -0.63
    ourgeois
    -0.62
    POSITIVE LOGITS
     gland
    0.83
    cium
    0.83
     bladder
    0.82
     curry
    0.82
    ghazi
    0.79
     colon
    0.77
    ãĥ¤
    0.76
    ctions
    0.74
    ãĤ¡
    0.74
    alyses
    0.74
    Activations Density 0.015%

    No Known Activations