© 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. 17301
    Prev
    Next
    INDEX
    Explanations

    countries

    oai_token-act-pair · gpt-3.5-turbo

    specific country names mentioned in the text

    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
    Sym
    -0.62
     propositions
    -0.59
    rase
    -0.59
    +=
    -0.58
    ctive
    -0.58
    shoot
    -0.58
    ¥
    -0.57
     constants
    -0.56
    Denver
    -0.56
    Berry
    -0.56
    POSITIVE LOGITS
     Airlines
    0.77
    uru
    0.74
     illegally
    0.74
     countryside
    0.74
     Springs
    0.74
    ipedia
    0.73
    pmwiki
    0.73
     TODAY
    0.72
     Reported
    0.71
     Minor
    0.71
    Activations Density 0.202%

    No Known Activations