© 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. 1-RES-JB
    11. 16102
    Prev
    Next
    INDEX
    Explanations

    mentions of continents

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic or continental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edi
    -0.79
     externalToEVAOnly
    -0.78
    verbs
    -0.75
    dos
    -0.73
    ND
    -0.72
    ymph
    -0.71
    ilts
    -0.71
    AK
    -0.69
    pos
    -0.68
    msg
    -0.68
    POSITIVE LOGITS
     Continent
    1.18
     continent
    1.06
     continents
    0.91
    inian
    0.84
    arium
    0.74
    naire
    0.73
    ãĤ¼ãĤ¦ãĤ¹
    0.71
    acebook
    0.70
    ãĥ¼ãĥĨãĤ£
    0.70
     Afric
    0.69
    Activations Density 0.007%

    No Known Activations