© 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. 13547
    Prev
    Next
    INDEX
    Explanations

    mentions of "strand" and related terms, potentially in the context of genetic testing or investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to strands of DNA or related genetic terminology

    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
    hammad
    -0.77
    iak
    -0.72
    urred
    -0.70
     laun
    -0.70
    pload
    -0.70
    blems
    -0.69
    sburgh
    -0.66
     tom
    -0.66
    yles
    -0.66
    opausal
    -0.65
    POSITIVE LOGITS
    angan
    0.95
     strand
    0.91
     strands
    0.83
    REL
    0.78
    adoes
    0.77
    ISH
    0.74
    velength
    0.73
    ARI
    0.73
    20439
    0.72
     Dalton
    0.70
    Activations Density 0.018%

    No Known Activations