© 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. 10-RES-JB
    11. 12462
    Prev
    Next
    INDEX
    Explanations

    locations or areas

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups and entities that play a role in societal dynamics

    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
    atever
    -0.76
    -+
    -0.76
     whichever
    -0.68
    =~
    -0.67
     Anyone
    -0.66
    issance
    -0.65
    =-=-
    -0.65
    runtime
    -0.64
    APTER
    -0.64
    ðĿ
    -0.63
    POSITIVE LOGITS
     downright
    1.06
     outright
    0.95
     even
    0.91
     prefer
    0.80
     argue
    0.75
     genuinely
    0.75
     worse
    0.74
    Nusra
    0.72
    hops
    0.71
     deliberately
    0.70
    Activations Density 0.312%

    No Known Activations