© 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. 22671
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences conveying a sense of absoluteness or certainty

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting the presence of "nothing."

    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
    orks
    -0.75
    anos
    -0.72
    eds
    -0.71
    ohyd
    -0.68
    visors
    -0.67
    visor
    -0.65
     Loans
    -0.65
    soon
    -0.65
    eda
    -0.63
    ahime
    -0.63
    POSITIVE LOGITS
     else
    0.96
     stopping
    0.88
     shameful
    0.87
     inherently
    0.86
     wrong
    0.86
     intrinsically
    0.84
     objectionable
    0.83
     worse
    0.80
     missing
    0.79
     sinister
    0.78
    Activations Density 0.064%

    No Known Activations