© 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. 8-RES-JB
    11. 2511
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or lack of information about identities

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "who" indicating uncertainty about identity or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    framework
    -0.80
    MER
    -0.70
    retion
    -0.69
    emin
    -0.68
    strip
    -0.67
    warning
    -0.64
     Globe
    -0.64
    emp
    -0.62
    esm
    -0.62
    urg
    -0.61
    POSITIVE LOGITS
     else
    1.08
    soever
    1.04
     owns
    0.94
     exactly
    0.93
     cares
    0.91
     cared
    0.87
    abouts
    0.86
     owes
    0.85
    dinand
    0.83
     participates
    0.82
    Activations Density 0.042%

    No Known Activations