© 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. 6-RES-JB
    11. 4181
    Prev
    Next
    INDEX
    Explanations

    single digit numbers followed by various symbols and text

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and steps related to processes or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etimes
    -0.73
    chy
    -0.73
    pers
    -0.71
    netflix
    -0.67
    elight
    -0.67
    eger
    -0.66
    "},"
    -0.65
    istical
    -0.65
    minecraft
    -0.64
    laim
    -0.64
    POSITIVE LOGITS
    Ĭ
    0.72
    ij士
    0.69
     onward
    0.68
     targ
    0.68
     onwards
    0.68
     Forth
    0.67
     Puzzles
    0.64
     à¤
    0.64
     Spells
    0.64
     Strat
    0.63
    Activations Density 0.096%

    No Known Activations