© 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. 2-RES-JB
    11. 494
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations and acronyms

    oai_token-act-pair · gpt-4-turbo

    terms related to technical device information, such as MAC addresses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to network protocols and device identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŃa
    -0.89
    shire
    -0.76
    idity
    -0.76
    ism
    -0.73
    ist
    -0.72
    ials
    -0.71
    zee
    -0.70
     Ronaldo
    -0.70
    ists
    -0.69
    alan
    -0.68
    POSITIVE LOGITS
    RESULTS
    0.82
    icipated
    0.82
    ategory
    0.81
    etheless
    0.76
    structed
    0.72
    è»
    0.71
    cised
    0.71
    Rect
    0.70
    FIR
    0.70
    METHOD
    0.68
    Activations Density 0.032%

    No Known Activations