© 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. 23079
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of retro-related items or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to "retro" themes or elements

    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
    gow
    -0.73
    avanaugh
    -0.72
    gans
    -0.71
     Parenthood
    -0.68
    Volume
    -0.66
    Export
    -0.66
     Secrets
    -0.66
    0000000
    -0.66
    UGE
    -0.66
    Translation
    -0.65
    POSITIVE LOGITS
    actively
    1.29
     retro
    1.17
    fitted
    1.05
    active
    1.04
    spective
    1.00
    gradation
    0.91
    spection
    0.87
    fits
    0.86
    grade
    0.84
    visor
    0.82
    Activations Density 0.007%

    No Known Activations