© 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. 4-RES-JB
    11. 10911
    Prev
    Next
    INDEX
    Explanations

    instructions starting with the word "If"

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or phrases that start with "If."

    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
    forth
    -0.74
    SPONSORED
    -0.70
    ãĤª
    -0.67
    natureconservancy
    -0.66
    âĵĺ
    -0.64
    %);
    -0.64
    rights
    -0.64
    ãĥŃ
    -0.63
    AAF
    -0.63
    rosse
    -0.62
    POSITIVE LOGITS
     you
    0.93
    rame
    0.91
    fy
    0.87
    yip
    0.82
    uana
    0.69
    phis
    0.67
     applicable
    0.66
    cfg
    0.64
     anything
    0.64
    soever
    0.63
    Activations Density 0.097%

    No Known Activations