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

    Neuronpedia

    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. 9-RES-JB
    11. 10086
    Prev
    Next
    INDEX
    Explanations

    terms or labels related to technical specifications or requirements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to official or standard protocols and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.95
    ourke
    -0.81
    hner
    -0.78
    eteenth
    -0.76
    conom
    -0.76
    ossession
    -0.75
    worn
    -0.75
    ":-
    -0.75
    bringing
    -0.74
    SEE
    -0.74
    POSITIVE LOGITS
     versions
    1.22
     implementations
    1.11
     ones
    1.11
     functionality
    1.11
     configuration
    1.09
     API
    1.09
     keywords
    1.08
     version
    1.07
     settings
    1.07
    izations
    1.04
    Activations Density 0.309%

    No Known Activations