© 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. 10-RES-JB
    11. 4613
    Prev
    Next
    INDEX
    Explanations

    statistical terms related to data analysis and economic indicators

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to income or earnings statistics

    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
    Maria
    -0.73
    ledge
    -0.68
    unity
    -0.68
    iHUD
    -0.68
    fab
    -0.67
    sic
    -0.67
    UV
    -0.64
     endif
    -0.64
    ItemThumbnailImage
    -0.64
    iki
    -0.64
    POSITIVE LOGITS
     each
    1.11
     respondents
    1.08
     households
    1.05
     different
    0.99
     various
    0.92
     percentile
    0.90
     OECD
    0.89
     respective
    0.89
     typical
    0.88
     counties
    0.87
    Activations Density 0.359%

    No Known Activations