© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 4426
    Prev
    Next
    INDEX
    Explanations

    words related to removal or elimination

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with purging or cleansing processes

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

    No Comments

    Negative Logits
    ETF
    -0.74
    SON
    -0.74
     Entry
    -0.71
    ellectual
    -0.71
    dn
    -0.70
    emate
    -0.67
    sett
    -0.65
    nan
    -0.65
    sson
    -0.65
    say
    -0.64
    POSITIVE LOGITS
     purge
    1.01
    utic
    0.76
    aneers
    0.75
     rituals
    0.75
     exorc
    0.74
     Tsukuyomi
    0.72
     ritual
    0.68
     cleaners
    0.68
     witches
    0.67
     gau
    0.67
    Activations Density 0.034%

    No Known Activations