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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 2332
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Condoleezza Rice."

    oai_token-act-pair · gpt-3.5-turbo

    words related to conditional statements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ku
    -0.74
    kaya
    -0.74
    DW
    -0.69
    Sham
    -0.69
     Witches
    -0.68
    sonian
    -0.67
    cca
    -0.65
    ngth
    -0.63
    ctica
    -0.63
    kick
    -0.63
    POSITIVE LOGITS
    itions
    0.97
    ensed
    0.96
    itional
    0.92
    ominium
    0.90
    uctor
    0.85
    Cond
    0.81
    itionally
    0.81
    riger
    0.81
     Cond
    0.81
    enser
    0.79
    Activations Density 0.007%

    No Known Activations