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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 16067
    Prev
    Next
    INDEX
    Explanations

    conditions and actions that are contingent on specific circumstances

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or statements prefaced by "unless" followed by actions or situations that the subject may find themselves in

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´
    -0.71
    word
    -0.68
    VG
    -0.66
    ãĥ³
    -0.62
    terson
    -0.60
    Topics
    -0.60
    same
    -0.59
    ãĥ«
    -0.59
     unanswered
    -0.58
    no
    -0.58
    POSITIVE LOGITS
     expressly
    1.01
     explicitly
    0.94
     specifically
    0.85
     somehow
    0.84
     absolutely
    0.81
    pecially
    0.77
     otherwise
    0.74
     interven
    0.73
     urgently
    0.72
     willfully
    0.72
    Activations Density 0.151%

    No Known Activations