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. 19784
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a person named "Jod" with varying suffixes

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character named "Jod."

    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
     Ago
    -0.73
    terday
    -0.68
     Leone
    -0.66
     Faul
    -0.63
     shorth
    -0.62
     Ki
    -0.59
    kson
    -0.57
     Polo
    -0.57
     Canter
    -0.56
     Lafayette
    -0.55
    POSITIVE LOGITS
    yssey
    1.36
    sworth
    1.05
    ragon
    1.05
    ouble
    1.02
    iamond
    1.02
    iox
    0.99
    amn
    0.98
    orf
    0.97
    iversity
    0.97
    rama
    0.96
    Activations Density 0.030%

    No Known Activations