© 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. 12794
    Prev
    Next
    INDEX
    Explanations

    phrases indicating discussions, negotiations, or agreements involving multiple parties

    oai_token-act-pair · gpt-3.5-turbo

    references to opposing groups or factions

    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
    pta
    -0.69
    DERR
    -0.68
    ķ
    -0.65
    nce
    -0.64
     Rapids
    -0.59
    ogle
    -0.58
    arton
    -0.57
     Prospect
    -0.57
    stad
    -0.57
     Tray
    -0.56
    POSITIVE LOGITS
     alike
    1.07
     sides
    0.99
     mutually
    0.98
     sexes
    0.98
     simultaneously
    0.97
     vying
    0.97
     equally
    0.96
     parties
    0.86
    '
    0.84
     agree
    0.83
    Activations Density 0.157%

    No Known Activations