© 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. 9-RES-JB
    11. 5859
    Prev
    Next
    INDEX
    Explanations

    the word "no" expressed with varying degrees of emphasis and contexts

    oai_token-act-pair · gpt-3.5-turbo

    the repeated expression of denial or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mund
    -0.71
    worn
    -0.65
     Suite
    -0.65
     debunked
    -0.64
    inguishable
    -0.63
    rn
    -0.61
    blogspot
    -0.60
    ivic
    -0.60
    ARY
    -0.59
     WATCHED
    -0.59
    POSITIVE LOGITS
    xious
    1.17
     longer
    0.96
    isy
    0.90
     harm
    0.86
    terday
    0.80
     mercy
    0.77
     matter
    0.76
    ct
    0.74
    oses
    0.73
    except
    0.73
    Activations Density 0.097%

    No Known Activations