© 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. 2-RES-JB
    11. 23407
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical details or expertise

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "technical."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.76
    xon
    -0.73
    inas
    -0.72
    velt
    -0.70
     Sheen
    -0.69
    vic
    -0.66
     Graves
    -0.66
     istg
    -0.65
    âĢ¢âĢ¢
    -0.63
    stellar
    -0.62
    POSITIVE LOGITS
     specifications
    0.95
     jargon
    0.93
    technical
    0.93
     glitches
    0.90
    idad
    0.87
     proficiency
    0.86
     technical
    0.86
     difficulties
    0.86
     considerations
    0.83
     sophistication
    0.82
    Activations Density 0.008%

    No Known Activations