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. 9-RES-JB
    6. 103
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical aspects of programming, particularly related to pointer management and memory management in programming languages like C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Photographer
    -0.76
     pics
    -0.72
     GoPro
    -0.71
     Militia
    -0.70
    phot
    -0.69
    bsite
    -0.68
    voy
    -0.68
    76561
    -0.68
    eyes
    -0.67
    mil
    -0.67
    POSITIVE LOGITS
     syntax
    1.46
     synt
    1.26
     semantics
    1.21
     Lisp
    1.16
     subclass
    1.16
     deprecated
    1.15
     tuple
    1.15
     implementations
    1.13
     Haskell
    1.13
     subscript
    1.12
    Activations Density 0.542%

    No Known Activations