© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 20462
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and positions

    oai_token-act-pair · gpt-3.5-turbo

    ordinal numbers and rankings in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patreon
    -0.62
     RELEASE
    -0.62
    IRC
    -0.60
     Constant
    -0.60
     Relationship
    -0.59
    Rules
    -0.56
     Sac
    -0.55
    Times
    -0.54
    ROR
    -0.54
     conventions
    -0.53
    POSITIVE LOGITS
     among
    0.92
     amongst
    0.91
     overall
    0.90
     nationally
    0.84
     percentile
    0.83
    retty
    0.82
     tier
    0.82
    Tier
    0.82
    swick
    0.76
     apiece
    0.76
    Activations Density 0.091%

    No Known Activations