© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 10950
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terms related to programming and technology, particularly focused on stack and trace-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to "stack" and related terms in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BAT
    -0.71
    ese
    -0.67
    eur
    -0.66
    ————
    -0.65
     annexed
    -0.64
    iator
    -0.63
    elope
    -0.62
    gdala
    -0.62
    undai
    -0.61
     concess
    -0.60
    POSITIVE LOGITS
    pole
    1.04
    stack
    1.00
    trace
    0.99
    Commerce
    0.96
    ings
    0.96
     overflow
    0.91
    Panel
    0.85
    mates
    0.84
    masters
    0.83
    mounted
    0.82
    Activations Density 0.043%

    No Known Activations