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. 7-RES-JB
    6. 15566
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person's name, "Reid."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Reid

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andise
    -0.97
    eatures
    -0.81
    omaly
    -0.79
    ruciating
    -0.75
    teenth
    -0.71
    cemic
    -0.69
     ILCS
    -0.68
    cer
    -0.65
    tesy
    -0.64
    thood
    -0.64
    POSITIVE LOGITS
    burgh
    0.83
    ifying
    0.83
    igan
    0.78
    ety
    0.72
     Reid
    0.71
    sburg
    0.70
    ifies
    0.70
    bro
    0.70
    IFIED
    0.69
     Mysteries
    0.69
    Activations Density 0.026%

    No Known Activations