© 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. 11-RES-JB
    11. 9854
    Prev
    Next
    INDEX
    Explanations

    countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to various countries and their economic or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advisory
    -0.54
     activ
    -0.54
    minist
    -0.53
     Tags
    -0.52
     signature
    -0.52
     meanings
    -0.51
    istor
    -0.51
     advertis
    -0.50
    TAG
    -0.50
     Accuracy
    -0.49
    POSITIVE LOGITS
     and
    0.84
     where
    0.77
     alone
    0.76
     or
    0.74
    's
    0.73
     Pradesh
    0.71
    Ì
    0.71
    ÃŃs
    0.68
    uador
    0.68
     (.
    0.68
    Activations Density 0.334%

    No Known Activations