© 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. 4-RES-JB
    11. 441
    Prev
    Next
    INDEX
    Explanations

    sequences with special characters and specific letters or numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and proper nouns associated with events or locations

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

    No Comments

    Negative Logits
    bags
    -0.74
    leaders
    -0.73
    gie
    -0.72
    ios
    -0.72
    doms
    -0.71
    boarding
    -0.71
    wig
    -0.70
    boxes
    -0.69
    mus
    -0.68
    geist
    -0.67
    POSITIVE LOGITS
    Æ
    0.78
    ©
    0.77
    kefeller
    0.77
    ñ
    0.74
    ¢
    0.74
    éĹĺ
    0.74
    ULTS
    0.70
    ±
    0.69
    Ãĥ
    0.69
    Ni
    0.68
    Activations Density 0.017%

    No Known Activations