© 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. 9-RES-JB
    11. 1029
    Prev
    Next
    INDEX
    Explanations

    activities and scenarios related to gambling

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to games and gambling

    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
    ãģ®å®
    -0.73
     breat
    -0.72
    Accessory
    -0.70
    mosp
    -0.70
     exports
    -0.67
    ufact
    -0.67
     NGOs
    -0.65
     Shelter
    -0.64
    irlf
    -0.63
     ambassador
    -0.62
    POSITIVE LOGITS
     lottery
    1.34
     arithmetic
    1.30
     quiz
    1.28
     maths
    1.27
     dice
    1.24
     guessing
    1.22
     algorithm
    1.22
     trivia
    1.21
     calculation
    1.20
     probabilities
    1.19
    Activations Density 1.191%

    No Known Activations