© 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. 7-RES-JB
    11. 10852
    Prev
    Next
    INDEX
    Explanations

    words related to negation or reversal, often in the form of prefixes like "un-" or "anti-"

    oai_token-act-pair · gpt-3.5-turbo

    words related to undignified or unrefined behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.80
    ppo
    -0.79
    Ĥİ
    -0.75
    auga
    -0.74
    姫
    -0.73
    tsky
    -0.73
    azines
    -0.72
    bley
    -0.72
    zzo
    -0.72
    ramid
    -0.69
    POSITIVE LOGITS
    etermined
    1.09
    oubt
    1.04
    iscovered
    1.03
    aunted
    0.99
    irect
    0.96
    ec
    0.95
    epend
    0.93
    ifferent
    0.91
    amed
    0.88
    etermin
    0.87
    Activations Density 0.011%

    No Known Activations