© 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. 7-RES-JB
    11. 24168
    Prev
    Next
    INDEX
    Explanations

    proper nouns with common prefixes "As" or "pen"

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms and uses of the letter "A" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {"
    -0.69
     Grayson
    -0.61
     Porsche
    -0.60
     Koz
    -0.59
     Zot
    -0.59
     Saskatchewan
    -0.59
     dime
    -0.57
     mean
    -0.56
     Shore
    -0.56
     Rats
    -0.55
    POSITIVE LOGITS
    wered
    1.03
    agus
    0.91
    allah
    0.90
    ylum
    0.85
    nown
    0.85
    ndra
    0.83
    ream
    0.83
    usa
    0.80
    aucas
    0.77
    adesh
    0.77
    Activations Density 0.051%

    No Known Activations