© 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. 9-RES-JB
    11. 20741
    Prev
    Next
    INDEX
    Explanations

    quantitative data mentioned in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to statistical data and percentages

    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
    press
    -0.74
    Reporting
    -0.73
     kidding
    -0.67
    killed
    -0.65
    Aid
    -0.64
    MAP
    -0.64
    hack
    -0.64
    »
    -0.63
    tackle
    -0.63
    ESE
    -0.63
    POSITIVE LOGITS
     each
    0.80
     others
    0.75
     every
    0.71
     any
    0.70
     the
    0.70
     either
    0.68
     whichever
    0.67
     other
    0.66
     neighbouring
    0.66
     another
    0.64
    Activations Density 0.203%

    No Known Activations