© 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. 1531
    Prev
    Next
    INDEX
    Explanations

    words related to replacement or substitution

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate substitution or replacement

    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
    raq
    -1.00
    vern
    -0.70
    hest
    -0.68
    keyes
    -0.65
    WA
    -0.64
    arta
    -0.64
    eb
    -0.63
    ern
    -0.63
    Import
    -0.63
    eller
    -0.63
    POSITIVE LOGITS
    ments
    0.86
     obsolete
    0.84
    mented
    0.72
    orate
    0.71
     redundant
    0.69
    itute
    0.69
    atives
    0.69
    utions
    0.68
     bulbs
    0.68
    ative
    0.67
    Activations Density 0.043%

    No Known Activations