© 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. 6-RES-JB
    11. 20671
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical distance or separation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize avoiding or distancing from something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.77
     teasp
    -0.74
    laughter
    -0.72
    SELECT
    -0.71
    Maker
    -0.70
    Must
    -0.70
    Congratulations
    -0.68
    BILL
    -0.68
    uid
    -0.67
    License
    -0.67
    POSITIVE LOGITS
     afar
    0.75
     anywhere
    0.72
     Hogwarts
    0.70
     home
    0.67
    ement
    0.65
     Anfield
    0.65
     Cuba
    0.64
     combust
    0.64
     anything
    0.64
     caring
    0.63
    Activations Density 0.060%

    No Known Activations