© 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. 8-RES-JB
    11. 3098
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers such as "1st," "2nd," and "3rd."

    oai_token-act-pair · gpt-3.5-turbo

    ordinal numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bath
    -0.76
    mbuds
    -0.76
     Canaver
    -0.73
    free
    -0.68
    etting
    -0.67
    Downloadha
    -0.67
    sav
    -0.63
    iannopoulos
    -0.62
    bos
    -0.62
    auna
    -0.61
    POSITIVE LOGITS
     Amendment
    1.01
     Circuit
    0.96
     installment
    0.94
    ousand
    0.92
     inning
    0.89
     percentile
    0.88
     Avenue
    0.83
    irty
    0.83
     Anniversary
    0.82
     century
    0.82
    Activations Density 0.044%

    No Known Activations