© 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. 3-RES-JB
    11. 15137
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ania" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, particularly those that end with the suffix 'ania' or 'anya'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glim
    -0.80
    lined
    -0.79
    spring
    -0.75
    straight
    -0.75
    points
    -0.72
    othe
    -0.72
    wcsstore
    -0.71
     srf
    -0.71
     carbohyd
    -0.69
    sy
    -0.69
    POSITIVE LOGITS
    utical
    0.88
     Resort
    0.80
    ania
    0.76
     Twain
    0.76
    ese
    0.75
     Islands
    0.74
     Mine
    0.73
    aceae
    0.71
     Franch
    0.71
    itaire
    0.70
    Activations Density 0.009%

    No Known Activations