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. 10-RES-JB
    6. 2146
    Prev
    Next
    INDEX
    Explanations

    strings related to coding, particularly Javascript and MongoDB commands

    oai_token-act-pair · gpt-3.5-turbo

    function calls and object methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grounding
    -0.70
     persecuted
    -0.70
     rocking
    -0.69
     doubted
    -0.68
     GOODMAN
    -0.66
     quo
    -0.65
     pir
    -0.64
      
    -0.64
     wise
    -0.62
     compromised
    -0.62
    POSITIVE LOGITS
    append
    1.28
    length
    1.24
    split
    1.23
    replace
    1.20
    prototype
    1.18
    remove
    1.16
    inner
    1.16
    push
    1.15
    apply
    1.15
    create
    1.11
    Activations Density 0.044%

    No Known Activations