© 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. 1-RES-JB
    11. 24049
    Prev
    Next
    INDEX
    Explanations

    references to the name "Charlie" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Char" from various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )=(
    -0.75
     Reloaded
    -0.74
    ãĢ
    -0.68
    ITNESS
    -0.66
    WARD
    -0.65
    UME
    -0.64
    EEE
    -0.64
    ATIVE
    -0.64
    CLASSIFIED
    -0.64
    æĸ¹
    -0.63
    POSITIVE LOGITS
    itably
    1.10
    coal
    1.04
    acters
    0.99
    iton
    0.91
    isma
    0.91
    itable
    0.90
     Char
    0.89
    usha
    0.84
    ilee
    0.84
    acha
    0.84
    Activations Density 0.011%

    No Known Activations