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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1503
    Prev
    Next
    INDEX
    Explanations

    the surname "Holt" with varying strengths of activation, potentially focusing more strongly on occurrences where it holds a higher relevance or significance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Holt

    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
     quo
    -0.79
    pires
    -0.71
    graded
    -0.71
    pired
    -0.69
    irement
    -0.68
    inent
    -0.66
    ystem
    -0.66
    omething
    -0.65
    esthetic
    -0.65
    grading
    -0.64
    POSITIVE LOGITS
    zman
    1.23
     Holt
    1.20
    bard
    0.87
     Conway
    0.82
    mann
    0.80
     Bolt
    0.79
    hurst
    0.78
    kamp
    0.78
    ãĤ¦ãĤ¹
    0.77
    gren
    0.77
    Activations Density 0.008%

    No Known Activations