© 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. 11-RES-JB
    11. 10277
    Prev
    Next
    INDEX
    Explanations

    the phrase "more or less."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating approximate quantities or similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EDITION
    -0.59
    wagen
    -0.58
     rapist
    -0.56
    Monitor
    -0.56
    ATT
    -0.55
    iasco
    -0.55
    ouse
    -0.55
     horizont
    -0.55
    CHR
    -0.53
     racket
    -0.52
    POSITIVE LOGITS
     less
    1.13
    nery
    1.02
    leans
    0.97
     fewer
    0.94
     Less
    0.90
     least
    0.87
    Less
    0.83
     lesser
    0.82
    gin
    0.77
    phans
    0.76
    Activations Density 0.032%

    No Known Activations