© 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. 8-RES-JB
    11. 20365
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completeness or intensity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to completeness or fullness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.76
    ramid
    -0.73
    gettable
    -0.70
     Continent
    -0.68
    xit
    -0.68
     Gathering
    -0.68
     burner
    -0.68
    ixtape
    -0.66
    irl
    -0.65
    RN
    -0.65
    POSITIVE LOGITS
     proportions
    1.08
     increments
    1.01
     mode
    0.90
     obscurity
    0.90
     fashion
    0.87
     terms
    0.87
     chronological
    0.85
     accordance
    0.85
     circumstances
    0.84
     circles
    0.83
    Activations Density 0.226%

    No Known Activations