© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 967
    Prev
    Next
    INDEX
    Explanations

    the word "substances" in various contexts

    oai_token-act-pair · gpt-4-turbo

    references to different types of substances, particularly those with potential toxicity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substances and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITAL
    -0.75
     Hawks
    -0.69
    addafi
    -0.68
    birds
    -0.64
    Bird
    -0.64
    thumbnails
    -0.64
    naire
    -0.64
    FN
    -0.62
    jin
    -0.62
    ais
    -0.61
    POSITIVE LOGITS
     substances
    1.20
     Flavoring
    0.85
     Substance
    0.84
    icone
    0.84
    ensing
    0.81
    itutes
    0.79
     liquids
    0.79
    ĸļ
    0.78
    amphetamine
    0.78
    wcsstore
    0.77
    Activations Density 0.010%

    No Known Activations