© 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. 8-RES-JB
    11. 22422
    Prev
    Next
    INDEX
    Explanations

    verbs related to consuming or consumption

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of consuming or consumption of various resources

    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
     Sharif
    -0.68
     awarding
    -0.67
    imov
    -0.63
     Pon
    -0.61
    mith
    -0.60
     Dee
    -0.57
     Shine
    -0.57
     Garry
    -0.57
     handshake
    -0.57
    aunder
    -0.56
    POSITIVE LOGITS
     habits
    0.98
    itures
    0.93
    iture
    0.92
     consumption
    0.88
    umes
    0.81
     Consumption
    0.78
    rior
    0.77
     calories
    0.77
    omics
    0.74
     expenditure
    0.74
    Activations Density 0.032%

    No Known Activations