© 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. 7-RES-JB
    11. 23386
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or historical precedents

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or societal precedents

    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
    wagen
    -0.85
    atron
    -0.77
    uttering
    -0.73
    yan
    -0.72
    otos
    -0.71
    ongs
    -0.71
    kie
    -0.70
    yne
    -0.70
    tein
    -0.69
    otin
    -0.68
    POSITIVE LOGITS
     precedent
    1.10
     preced
    0.95
     precedence
    0.82
    setting
    0.76
    DragonMagazine
    0.75
    chall
    0.72
     Authority
    0.66
     enshr
    0.66
    LR
    0.65
    faced
    0.65
    Activations Density 0.037%

    No Known Activations