© 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. 7-RES-JB
    11. 21624
    Prev
    Next
    INDEX
    Explanations

    instances where someone is unable to do something or experiencing difficulties

    oai_token-act-pair · gpt-3.5-turbo

    the term "unable" in various contexts related to inability or incapacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gone
    -0.73
    soType
    -0.68
    nice
    -0.66
    eg
    -0.65
    adows
    -0.63
     Tradition
    -0.62
    ervative
    -0.61
    oak
    -0.61
    ramid
    -0.61
    positive
    -0.60
    POSITIVE LOGITS
     compe
    0.86
    ioned
    0.84
    icably
    0.79
     necessarily
    0.78
    untarily
    0.76
     adequately
    0.76
     afford
    0.73
    oooooooo
    0.72
     feas
    0.70
    iquid
    0.69
    Activations Density 0.028%

    No Known Activations