© 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. 10144
    Prev
    Next
    INDEX
    Explanations

    sequences of characters or symbols that don't form meaningful words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols often related to encoding or formatting

    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
    ongs
    -0.90
    ourke
    -0.83
    imentary
    -0.79
    APH
    -0.75
    erker
    -0.69
    anmar
    -0.66
    olicited
    -0.66
    utical
    -0.65
    videos
    -0.65
    ovie
    -0.65
    POSITIVE LOGITS
    pmwiki
    0.90
    entimes
    0.88
    wcsstore
    0.79
    É
    0.78
    ãĥ
    0.76
    deck
    0.76
    ËĪ
    0.74
    ãĤ¢
    0.70
    ãĥ¢
    0.70
    ername
    0.69
    Activations Density 0.015%

    No Known Activations