© 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. 6546
    Prev
    Next
    INDEX
    Explanations

    references to the action of eating

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "eat" and its variations, indicating a focus on themes related to eating

    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
    worthiness
    -0.73
    channelAvailability
    -0.72
     Stellar
    -0.71
     Aus
    -0.69
     Gemini
    -0.69
     Angola
    -0.67
     Lash
    -0.66
     Nichols
    -0.65
     Nich
    -0.64
     Jenner
    -0.64
    POSITIVE LOGITS
     habits
    0.99
    eteria
    0.95
     breakfast
    0.95
    anut
    0.92
     eaten
    0.92
     meals
    0.91
     cake
    0.90
     foods
    0.89
     eat
    0.88
     nutrit
    0.88
    Activations Density 0.036%

    No Known Activations