© 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. 22430
    Prev
    Next
    INDEX
    Explanations

    usernames or names in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    specific identifiers and nouns related to usernames, lists, and entities

    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
     Cub
    -0.61
     Mug
    -0.56
     Negro
    -0.56
     FedEx
    -0.53
    zac
    -0.52
    othermal
    -0.52
    uba
    -0.52
    ivable
    -0.51
     alike
    -0.50
    obo
    -0.50
    POSITIVE LOGITS
    and
    0.97
     &
    0.97
    &
    0.96
     AND
    0.94
    /
    0.94
    /
    0.86
     and
    0.81
     or
    0.80
    andowski
    0.76
    ands
    0.75
    Activations Density 0.641%

    No Known Activations