© 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. 6-RES-JB
    11. 3015
    Prev
    Next
    INDEX
    Explanations

    verbs related to decision-making, specifically the action of "casting"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cast" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.83
    ĸļ
    -0.70
    £ı
    -0.69
     Hamp
    -0.65
    ¥µ
    -0.64
    psey
    -0.62
     proble
    -0.61
     Situation
    -0.61
     psychiat
    -0.58
     overcrowd
    -0.58
    POSITIVE LOGITS
    aways
    1.14
    igating
    1.00
    aine
    0.95
    otom
    0.94
    rating
    0.92
    igated
    0.91
    rated
    0.90
     casts
    0.90
    ration
    0.87
    offs
    0.84
    Activations Density 0.014%

    No Known Activations