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. 11-RES-JB
    6. 24356
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming and software development, specifically focusing on stack-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to "stack" and related concepts in programming or software development

    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
    ————
    -0.76
    BAT
    -0.73
    ese
    -0.67
     Ultron
    -0.62
    pard
    -0.62
     mell
    -0.61
    orie
    -0.61
    icals
    -0.60
    ICO
    -0.60
    bered
    -0.59
    POSITIVE LOGITS
    trace
    1.11
    stack
    1.01
    mounted
    0.97
     overflow
    0.95
    pole
    0.93
    ings
    0.86
     trace
    0.84
    over
    0.84
    Commerce
    0.84
     traces
    0.83
    Activations Density 0.083%

    No Known Activations