© 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. 8-RES-JB
    11. 2549
    Prev
    Next
    INDEX
    Explanations

    text related to sharing, posting, providing feedback, and reviewing content

    oai_token-act-pair · gpt-3.5-turbo

    terms related to content creation and user engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.73
    ¥µ
    -0.73
    osi
    -0.71
     curfew
    -0.67
    sw
    -0.64
    ©¶æ¥µ
    -0.64
    armac
    -0.64
     neoc
    -0.63
     manslaughter
    -0.62
    agall
    -0.61
    POSITIVE LOGITS
     aloud
    0.89
    mith
    0.89
    ynthesis
    0.87
    pace
    0.86
    uggest
    0.85
    heet
    0.85
    peed
    0.84
     pertaining
    0.83
    poons
    0.82
     submitted
    0.82
    Activations Density 0.360%

    No Known Activations