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

    Neuronpedia

    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. 2-RES-JB
    11. 381
    Prev
    Next
    INDEX
    Explanations

    the surname "McCarthy"

    oai_token-act-pair · gpt-4-turbo

    mentions or occurrences of the word "McCarthy"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "McCarthy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orable
    -0.72
    gered
    -0.69
    orative
    -0.68
    LOAD
    -0.67
    ultan
    -0.66
    inence
    -0.65
    chest
    -0.64
    rator
    -0.64
    ĻĤ
    -0.64
    joining
    -0.63
    POSITIVE LOGITS
     McCarthy
    1.03
    ite
    0.81
    igans
    0.81
    isms
    0.77
    ites
    0.76
    loo
    0.72
    Afee
    0.71
    omics
    0.70
    ism
    0.70
    atown
    0.67
    Activations Density 0.006%

    No Known Activations