© 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. 2423
    Prev
    Next
    INDEX
    Explanations

    statistics or numerical values emphasized in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "just" in various contexts

    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
    antis
    -0.63
    anon
    -0.58
    stress
    -0.57
    Factor
    -0.57
     trave
    -0.57
     subsequ
    -0.57
    risk
    -0.56
     includ
    -0.56
    sac
    -0.56
     PLUS
    -0.55
    POSITIVE LOGITS
    ifiable
    1.24
    ifications
    1.12
    ices
    0.92
    ifiers
    0.86
     shy
    0.85
    ifier
    0.85
    if
    0.83
    IFIC
    0.82
    itia
    0.82
    iciary
    0.78
    Activations Density 0.070%

    No Known Activations