© 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. 10-RES-JB
    11. 14116
    Prev
    Next
    INDEX
    Explanations

    names of news organizations and research-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lowly
    -0.77
     pleas
    -0.73
     goddamn
    -0.72
    theless
    -0.67
     darn
    -0.64
     includ
    -0.63
     exact
    -0.63
     pend
    -0.63
     meas
    -0.62
     rooting
    -0.62
    POSITIVE LOGITS
     Ltd
    1.03
     Syndrome
    0.95
     Laboratories
    0.91
     Limited
    0.91
     Collection
    0.90
     Publishers
    0.90
     Collective
    0.88
     Club
    0.88
    naire
    0.87
     Productions
    0.86
    Activations Density 0.381%

    No Known Activations