© 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. 3-RES-JB
    11. 1739
    Prev
    Next
    INDEX
    Explanations

    names of famous literary figures and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Conan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pher
    -0.84
    sie
    -0.77
    onday
    -0.76
    spr
    -0.75
    ify
    -0.74
    iamond
    -0.73
    ifying
    -0.72
    stones
    -0.71
    sburgh
    -0.71
    blance
    -0.71
    POSITIVE LOGITS
    icum
    0.87
     Conan
    0.83
     Barbarian
    0.81
    ulhu
    0.79
     Newport
    0.75
    omics
    0.69
    jiang
    0.66
    USS
    0.66
     tabletop
    0.65
     Marines
    0.65
    Activations Density 0.019%

    No Known Activations