© 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. 0-RES-JB
    11. 6850
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically those related to people or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific markers related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ton
    -0.72
     Dunk
    -0.72
    ror
    -0.71
    tor
    -0.69
     Cher
    -0.68
     countdown
    -0.67
    vernment
    -0.66
     barrel
    -0.66
    weet
    -0.63
     VER
    -0.63
    POSITIVE LOGITS
    aho
    3.80
     Pascal
    1.33
    bring
    1.12
    asca
    1.04
    entity
    0.98
     Huang
    0.98
    cells
    0.95
     PDT
    0.95
     Hands
    0.94
     helicop
    0.92
    Activations Density 0.076%

    No Known Activations