© 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. 3-RES-JB
    11. 1731
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly those associated with news or events

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those associated with notable events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solitaire
    -0.84
     Goose
    -0.78
     bucks
    -0.76
    naire
    -0.74
     Colossus
    -0.73
    sburgh
    -0.71
     Scotch
    -0.70
    arget
    -0.70
     deform
    -0.69
     boulder
    -0.69
    POSITIVE LOGITS
    ovic
    1.05
     Rahman
    1.05
     Hussain
    1.03
    iyah
    1.02
     ibn
    0.98
     Ahmed
    0.96
     Sheikh
    0.95
     Mahm
    0.95
     Ahmad
    0.92
     Ali
    0.87
    Activations Density 0.013%

    No Known Activations