© 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. 9-RES-JB
    11. 1059
    Prev
    Next
    INDEX
    Explanations

    names, particularly those with variations in spelling

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly related to notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breast
    -0.69
     IMAGES
    -0.68
     crop
    -0.61
     notch
    -0.61
     crochet
    -0.61
     cereal
    -0.60
     stewards
    -0.59
    llor
    -0.59
     senseless
    -0.59
     valiant
    -0.58
    POSITIVE LOGITS
    abeth
    1.17
    abet
    0.90
    ée
    0.80
    onde
    0.77
    otte
    0.77
     Musk
    0.76
     guiActiveUn
    0.73
    ande
    0.73
    OY
    0.71
    icio
    0.70
    Activations Density 0.103%

    No Known Activations