© 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. 7768
    Prev
    Next
    INDEX
    Explanations

    references to spending time with friends

    oai_token-act-pair · gpt-3.5-turbo

    references to friendship and social connections

    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
    rection
    -0.72
    Ħ¢
    -0.71
    ©¶æ
    -0.70
    phas
    -0.67
    orney
    -0.65
     untreated
    -0.63
    elsius
    -0.62
    plet
    -0.61
    agnetic
    -0.59
    æ©Ł
    -0.59
    POSITIVE LOGITS
    hips
    1.27
    liest
    1.04
    folk
    1.00
    liness
    0.99
    lier
    0.96
    hip
    0.88
     acquaintances
    0.86
     whom
    0.81
     who
    0.80
    ships
    0.78
    Activations Density 0.058%

    No Known Activations