© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    fractions or percentages

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proportions or fractions

    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
    arella
    -0.70
     Levin
    -0.65
    uyomi
    -0.63
     aside
    -0.63
    ucci
    -0.61
     Clash
    -0.59
     reintrodu
    -0.58
    ãĤ¶
    -0.57
    pedia
    -0.57
     Dictionary
    -0.56
    POSITIVE LOGITS
    icial
    0.70
     dozen
    0.69
    course
    0.69
    ths
    0.68
    hops
    0.64
     GDP
    0.64
    perties
    0.64
     Sevent
    0.63
     respondents
    0.62
    Initialized
    0.61
    Activations Density 0.088%

    No Known Activations