Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 1982
    Prev
    Next
    INDEX
    Explanations

    specific terms related to programming syntax, such as "argument", "field", "array", and "function"

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and parameters related to programming and function arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fare
    -0.77
    egal
    -0.76
    waters
    -0.75
    shoot
    -0.74
     millenn
    -0.73
     simul
    -0.73
    bill
    -0.72
    ilers
    -0.70
     resil
    -0.69
    conom
    -0.69
    POSITIVE LOGITS
     names
    1.00
     passed
    0.88
     parameter
    0.85
     params
    0.84
     headers
    0.83
     defaults
    0.82
     labels
    0.82
    param
    0.81
     encoded
    0.81
     specifying
    0.80
    Activations Density 0.106%

    No Known Activations