© 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. 11598
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals, potentially in academic or professional settings

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or entities, particularly in a formal context

    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
    phia
    -0.75
    round
    -0.75
    quartered
    -0.73
    estyles
    -0.73
    capital
    -0.72
    estones
    -0.71
    DragonMagazine
    -0.70
    grounds
    -0.69
    Reviewer
    -0.68
    isec
    -0.66
    POSITIVE LOGITS
     Zhang
    0.91
     Fuk
    0.82
     Zhao
    0.82
     Liang
    0.81
     et
    0.80
     Peng
    0.74
     Wang
    0.70
     Keller
    0.69
     Foley
    0.69
     Wilkinson
    0.68
    Activations Density 0.063%

    No Known Activations