© 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. 2-RES-JB
    11. 3889
    Prev
    Next
    INDEX
    Explanations

    food-related items or lists

    oai_token-act-pair · gpt-3.5-turbo

    items related to shopping and food preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.83
     scrap
    -0.67
    ĸļ
    -0.66
    ername
    -0.63
     legisl
    -0.60
     hust
    -0.59
    xual
    -0.59
     citiz
    -0.58
     mathemat
    -0.58
     tink
    -0.58
    POSITIVE LOGITS
    Recommended
    0.81
    References
    0.77
    Anonymous
    0.76
    ItemThumbnailImage
    0.75
    ................................................................
    0.73
    âĵĺ
    0.73
    ONSORED
    0.73
    ccording
    0.73
    Cost
    0.71
    Advertisements
    0.70
    Activations Density 1.175%

    No Known Activations