© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11251
    Prev
    Next
    INDEX
    Explanations

    cases of mistaken identity or belief

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mistaken" and related concepts of misunderstanding or confusion

    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
    ŃĶ
    -0.73
    rollers
    -0.68
    onse
    -0.66
    boats
    -0.63
    iaries
    -0.63
    ILA
    -0.62
    ffield
    -0.62
    tsky
    -0.62
    olition
    -0.61
    essen
    -0.61
    POSITIVE LOGITS
     impression
    0.88
     mistaken
    0.85
     perceptions
    0.75
    uca
    0.70
    arget
    0.69
     notions
    0.67
     wrongly
    0.67
    pelled
    0.66
     Tradable
    0.66
     assumptions
    0.66
    Activations Density 0.079%

    No Known Activations