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. 11-RES-JB
    6. 4375
    Prev
    Next
    INDEX
    Explanations

    programming code syntax patterns

    oai_token-act-pair · gpt-3.5-turbo

    elements related to data structures and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stability
    -0.66
    ulence
    -0.64
     tremend
    -0.62
    thening
    -0.59
     peg
    -0.59
     fragment
    -0.59
     plaster
    -0.58
     neigh
    -0.58
     swell
    -0.58
    lihood
    -0.57
    POSITIVE LOGITS
     pressed
    1.34
     pushed
    1.32
    changed
    1.29
     checked
    1.29
     clicked
    1.27
    ended
    1.27
     touched
    1.27
     kissed
    1.26
    pressed
    1.26
    lished
    1.25
    Activations Density 0.265%

    No Known Activations