© 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. 813
    Prev
    Next
    INDEX
    Explanations

    names of places or people with a specific emphasis on the last part of the name

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns, particularly those of people and places

    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
     Villa
    -0.77
     Squirrel
    -0.73
     Tablet
    -0.72
     Buffalo
    -0.71
    rals
    -0.70
     Reloaded
    -0.70
     PB
    -0.69
     420
    -0.69
     Butler
    -0.69
     Totem
    -0.67
    POSITIVE LOGITS
    is
    1.67
    IS
    1.53
    ises
    1.44
    isin
    1.30
    ise
    1.29
    isf
    1.16
    ISC
    1.13
    isi
    1.12
    iss
    1.12
    isd
    1.11
    Activations Density 0.117%

    No Known Activations