© 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. 15911
    Prev
    Next
    INDEX
    Explanations

    phrases related to judgment and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe conditions of consideration and evaluation

    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
    alion
    -0.84
    rower
    -0.82
    ioch
    -0.80
    erva
    -0.78
    someone
    -0.77
    mie
    -0.76
    culosis
    -0.76
    Luck
    -0.75
    erity
    -0.75
    etz
    -0.75
    POSITIVE LOGITS
     equivalents
    1.31
     ones
    1.26
     replacements
    1.23
     extensions
    1.15
     indicators
    1.13
     markers
    1.11
     staples
    1.11
     trophies
    1.11
     anomalies
    1.11
     respectively
    1.10
    Activations Density 0.588%

    No Known Activations