Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10579
    Prev
    Next
    INDEX
    Explanations

    words or phrases that include special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    the character "ĵ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olis
    -0.72
    aries
    -0.71
    ako
    -0.71
    apse
    -0.69
    arella
    -0.67
    urtle
    -0.67
    ignment
    -0.64
    oldemort
    -0.63
    ourced
    -0.63
    ouched
    -0.63
    POSITIVE LOGITS
    âĸĵ
    0.95
    DIT
    0.94
    scar
    0.81
    ¡
    0.80
    ĵ
    0.79
    CEPT
    0.77
    URI
    0.75
    BLE
    0.75
    é¾įåĸļ士
    0.74
    ÃĽ
    0.74
    Activations Density 0.016%

    No Known Activations