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. 4755
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets involving standard input/output

    oai_token-act-pair · gpt-3.5-turbo

    elements of C++ programming syntax and specific library includes

    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
    Featured
    -0.77
    soDeliveryDate
    -0.75
     Seller
    -0.75
     monet
    -0.74
    ento
    -0.73
     Karma
    -0.68
    zees
    -0.68
     Yel
    -0.67
    ón
    -0.67
     Guilty
    -0.67
    POSITIVE LOGITS
     pointer
    1.17
     sizeof
    1.05
     ptr
    0.99
     buffer
    0.98
     pointers
    0.95
     printf
    0.92
    buffer
    0.91
     buffers
    0.88
    atomic
    0.88
    addr
    0.88
    Activations Density 0.207%

    No Known Activations