© 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. 10-RES-JB
    11. 12414
    Prev
    Next
    INDEX
    Explanations

    quantitative superlatives or comparisons such as "most" or "least," often related to various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cia
    -0.84
    acus
    -0.80
    rompt
    -0.78
    amily
    -0.75
    agine
    -0.73
    heid
    -0.68
    brew
    -0.68
    selves
    -0.66
    arent
    -0.65
    saf
    -0.63
    POSITIVE LOGITS
     bang
    0.95
     stringent
    0.82
     extensive
    0.82
     mileage
    0.82
     attention
    0.79
     egregious
    0.79
     votes
    0.76
     successes
    0.76
     frequent
    0.74
     recent
    0.73
    Activations Density 0.057%

    No Known Activations