Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4713
    Prev
    Next
    INDEX
    Explanations

    instances of the word "if" followed by a statement

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akia
    -0.70
    azo
    -0.68
    isi
    -0.66
    enos
    -0.65
     Pledge
    -0.60
    insula
    -0.60
    FTWARE
    -0.60
    urga
    -0.58
    ciating
    -0.57
    hs
    -0.57
    POSITIVE LOGITS
    fy
    1.20
     indeed
    1.08
     anything
    1.03
    rame
    1.00
     ever
    0.97
     not
    0.95
     applicable
    0.87
    tar
    0.87
     necessary
    0.84
     possible
    0.84
    Activations Density 0.073%

    No Known Activations