© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18773
    Prev
    Next
    INDEX
    Explanations

    software-related terms, specifically related to operating systems and applications

    oai_token-act-pair · gpt-3.5-turbo

    references to software, technology, or computer systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behalf
    -0.59
    amina
    -0.58
    istrate
    -0.58
    nai
    -0.58
     unspecified
    -0.57
    gently
    -0.54
     Became
    -0.54
    ertodd
    -0.53
     promptly
    -0.53
    orum
    -0.53
    POSITIVE LOGITS
     counterparts
    1.18
     predecessors
    1.14
     counterpart
    0.95
     predecessor
    0.88
     except
    0.81
     equivalents
    0.81
     elsewhere
    0.81
     nor
    0.78
     previous
    0.77
     offerings
    0.75
    Activations Density 0.606%

    No Known Activations