© 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. 1-RES-JB
    11. 20188
    Prev
    Next
    INDEX
    Explanations

    words related to particular, distinct, or specified items or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "specific."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kenn
    -0.78
     Tycoon
    -0.77
     largeDownload
    -0.76
     McGee
    -0.75
     Feldman
    -0.74
     Alive
    -0.73
    ulton
    -0.71
    ington
    -0.68
     Kirin
    -0.68
     Dickinson
    -0.68
    POSITIVE LOGITS
     identifiable
    1.08
    ities
    0.97
     particulars
    0.85
     contextual
    0.84
     embodiments
    0.84
     geographic
    0.83
    iating
    0.83
     geographical
    0.82
    iates
    0.82
    iations
    0.82
    Activations Density 0.013%

    No Known Activations