© 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. 23673
    Prev
    Next
    INDEX
    Explanations

    non-alphabetic characters

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions and uncertainties

    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
     migration
    -0.79
     cross
    -0.69
     carriage
    -0.66
     celebr
    -0.65
     migr
    -0.64
     glyph
    -0.64
     downstream
    -0.63
     cannabis
    -0.63
     potion
    -0.62
     analges
    -0.61
    POSITIVE LOGITS
    Answer
    1.34
    --------------------------------------------------------
    0.93
    =-=-=-=-=-=-=-=-
    0.90
    Question
    0.89
    ãĥ¯ãĥ³
    0.89
    ?????-?????-
    0.89
    Anyway
    0.87
    Spoiler
    0.86
    ãĥ¤
    0.86
    Trivia
    0.85
    Activations Density 0.177%

    No Known Activations