© 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. 9-RES-JB
    11. 23880
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and their characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive elements related to cities and their characteristics

    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
    successfully
    -0.84
    ģĸ
    -0.84
     Incre
    -0.78
    Dispatch
    -0.77
     Replacement
    -0.74
    ãĥīãĥ©
    -0.71
    EStream
    -0.70
    handler
    -0.69
    ãĥ¯
    -0.69
    DCS
    -0.68
    POSITIVE LOGITS
     bustling
    1.25
     spacious
    1.17
     atmosphere
    1.12
     crowded
    1.10
     deserted
    1.08
     populated
    1.08
     winters
    1.07
     cramped
    1.05
     desolate
    1.05
     rainy
    1.03
    Activations Density 0.763%

    No Known Activations