© 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. 11-RES-JB
    11. 1284
    Prev
    Next
    INDEX
    Explanations

    proper nouns with a location indicator, specifically related to news and events

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks, indicating the conclusion of thoughts or statements

    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
    ovic
    -0.67
    erity
    -0.59
    staking
    -0.58
     impart
    -0.56
    nuts
    -0.55
     trolling
    -0.55
     kidnapping
    -0.55
     guiding
    -0.55
     spo
    -0.54
     honour
    -0.54
    POSITIVE LOGITS
    Y
    1.16
    J
    0.97
    C
    0.95
    D
    0.92
    Va
    0.90
    Ire
    0.87
    Ireland
    0.86
    B
    0.83
    Jer
    0.82
    E
    0.81
    Activations Density 0.015%

    No Known Activations