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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 1016
    Prev
    Next
    INDEX
    Explanations

    words related to a sports team named "Blues"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Blues."

    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
    ILY
    -0.87
    lying
    -0.75
    Population
    -0.74
    antly
    -0.74
    igators
    -0.74
    inosaur
    -0.73
    Political
    -0.72
    ortion
    -0.70
    igated
    -0.68
    icles
    -0.68
    POSITIVE LOGITS
    hift
    1.28
     Blues
    0.96
    hirt
    0.94
    creen
    0.93
    berries
    0.85
     blues
    0.78
    ignt
    0.72
    forth
    0.70
    berry
    0.69
    erk
    0.69
    Activations Density 0.006%

    No Known Activations