© 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. 7-RES-JB
    11. 17177
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of knowledge or certainty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I had no idea."

    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
    iki
    -0.72
    Pers
    -0.69
    inka
    -0.67
    die
    -0.63
    rup
    -0.62
    Tro
    -0.62
    pu
    -0.61
    Minor
    -0.60
    DF
    -0.60
    visor
    -0.60
    POSITIVE LOGITS
     whatsoever
    1.09
     why
    0.87
     how
    0.86
    ledged
    0.80
     WHY
    0.77
     whence
    0.77
    ariat
    0.77
     whats
    0.74
     squat
    0.72
     what
    0.72
    Activations Density 0.036%

    No Known Activations