Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2543
    Prev
    Next
    INDEX
    Explanations

    mentions of particular names in the format "Roy Ritchie" and "Charlie Magee."

    oai_token-act-pair · gpt-3.5-turbo
    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
     cos
    -0.66
     inactive
    -0.61
    cffff
    -0.61
    ings
    -0.60
     footing
    -0.59
     tom
    -0.59
     aging
    -0.58
     nar
    -0.58
    tered
    -0.58
     advers
    -0.57
    POSITIVE LOGITS
    ?????-
    0.85
    Ü
    0.84
    ?????-?????-
    0.82
    QUI
    0.80
    âĵĺ
    0.79
    Db
    0.77
    Rail
    0.76
    effects
    0.75
    arta
    0.75
    gex
    0.74
    Activations Density 0.187%

    No Known Activations