Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4658
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals and news events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of familial relationships and individuals involved in significant events

    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
     mode
    -0.68
    autions
    -0.64
    ciplinary
    -0.61
     nonetheless
    -0.60
    direction
    -0.60
     preset
    -0.59
     precaution
    -0.58
     anecd
    -0.58
    Disclaimer
    -0.58
     rede
    -0.58
    POSITIVE LOGITS
    thood
    0.86
    addafi
    0.77
     deceased
    0.71
     martyr
    0.71
     namesake
    0.69
     slain
    0.68
    amily
    0.68
     family
    0.65
     beloved
    0.65
     victims
    0.64
    Activations Density 0.848%

    No Known Activations