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. 21152
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or sequences in code snippets

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to programming and data structures

    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
     veto
    -0.69
     gri
    -0.65
     NRA
    -0.64
     plac
    -0.63
     Freak
    -0.61
     Compet
    -0.59
     broch
    -0.59
     Krug
    -0.59
     Particip
    -0.59
     buyer
    -0.59
    POSITIVE LOGITS
    000000
    1.30
    0000000
    1.29
    00000000
    1.26
    0000
    1.23
    0000000000000000
    1.22
    9999
    1.19
    00000
    1.13
    px
    1.13
    dfx
    1.09
    ÏĢ
    1.01
    Activations Density 0.104%

    No Known Activations