© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3604
    Prev
    Next
    INDEX
    Explanations

    words that indicate computer code syntax

    oai_token-act-pair · gpt-3.5-turbo

    references to traits of dishonesty or treachery

    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
    intosh
    -0.83
    dos
    -0.78
    ertodd
    -0.74
    elaide
    -0.73
    daq
    -0.72
    rodu
    -0.72
    yles
    -0.68
    bons
    -0.64
    prus
    -0.64
    tel
    -0.63
    POSITIVE LOGITS
    aries
    1.04
     tru
    1.01
    ances
    0.94
    arily
    0.93
    ary
    0.91
    shire
    0.89
    icity
    0.86
    arial
    0.83
    ariat
    0.79
    aires
    0.76
    Activations Density 0.031%

    No Known Activations