© 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. 19461
    Prev
    Next
    INDEX
    Explanations

    keywords related to business, finance, politics, and administration

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to products, services, and charitable contributions

    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
     acron
    -0.69
    urches
    -0.69
    acements
    -0.67
    ositories
    -0.66
    ernels
    -0.65
    hots
    -0.65
    tons
    -0.63
    ories
    -0.63
    ths
    -0.63
     trophies
    -0.62
    POSITIVE LOGITS
    igmatic
    0.83
     standpoint
    0.76
    walker
    0.75
     phenotype
    0.74
    ogram
    0.74
     nucleus
    0.73
     cutter
    0.72
     lover
    0.71
     instance
    0.70
    worker
    0.70
    Activations Density 0.585%

    No Known Activations