© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 22883
    Prev
    Next
    INDEX
    Explanations

    proper names or nicknames of individuals

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    knit
    -0.81
     CLIENT
    -0.75
    inary
    -0.73
    MpServer
    -0.72
    alysed
    -0.72
    verages
    -0.71
    Reviewer
    -0.70
    paren
    -0.70
    iqueness
    -0.70
    pection
    -0.69
    POSITIVE LOGITS
     Andersen
    1.02
     Johnson
    0.95
     Boone
    0.94
     Cohn
    0.90
     Mang
    0.89
     Robinson
    0.89
     Jackson
    0.89
     Roberts
    0.89
     Cohen
    0.84
     Gund
    0.84
    Activations Density 0.049%

    No Known Activations