© 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. 19307
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a statement or opinion being expressed

    oai_token-act-pair · gpt-3.5-turbo

    expressions involving the word "say" and its variations

    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
    ells
    -0.67
    pes
    -0.66
    figure
    -0.66
    imeo
    -0.65
    emort
    -0.65
    ancies
    -0.65
    catentry
    -0.61
     obser
    -0.60
    ilan
    -0.60
    etimes
    -0.60
    POSITIVE LOGITS
     that
    1.23
     otherwise
    0.91
     goodbye
    0.90
    that
    0.89
     THAT
    0.85
     thats
    0.77
     we
    0.76
     they
    0.71
     there
    0.70
     unequivocally
    0.69
    Activations Density 0.144%

    No Known Activations