© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    phrases indicating differences or contrasts between various entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases comparing differences between entities or concepts

    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
    tti
    -0.90
    merga
    -0.78
    isphere
    -0.75
    taboola
    -0.69
    Limited
    -0.69
    aley
    -0.68
    ranked
    -0.66
    iband
    -0.64
    Dur
    -0.63
    bard
    -0.63
    POSITIVE LOGITS
     ours
    1.08
     ordinary
    1.01
     theirs
    0.93
     others
    0.92
     anything
    0.91
     other
    0.90
     yours
    0.89
     what
    0.86
     typical
    0.83
     previous
    0.82
    Activations Density 0.085%

    No Known Activations