© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5707
    Prev
    Next
    INDEX
    Explanations

    mentions of "Pilgrimage" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Pil" in various contexts related to themes or subjects potentially linked to politics or piloting

    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
     Carbuncle
    -0.81
     Baird
    -0.69
    !/
    -0.68
     favors
    -0.66
    Ļ½
    -0.65
    anwhile
    -0.63
     Catalyst
    -0.62
     Byr
    -0.61
    liness
    -0.61
    lies
    -0.60
    POSITIVE LOGITS
    chard
    1.18
    oted
    0.97
    cipled
    0.95
    nington
    0.94
    awar
    0.93
    monary
    0.91
    ots
    0.90
    crow
    0.90
    igree
    0.90
    iferation
    0.89
    Activations Density 0.027%

    No Known Activations