© 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. 8-RES-JB
    11. 11136
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a relative distance or deviation from a point of reference

    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
    liction
    -0.74
    dump
    -0.73
    isin
    -0.71
    uary
    -0.71
    might
    -0.68
    ilage
    -0.67
    icks
    -0.65
    while
    -0.64
    çī
    -0.64
    illary
    -0.64
    POSITIVE LOGITS
     ideal
    0.89
     perfect
    0.83
     conclusive
    0.83
     satisfactory
    0.77
     exhaustive
    0.76
     uncommon
    0.75
     definitive
    0.73
     optimal
    0.72
     resembling
    0.72
    icable
    0.70
    Activations Density 0.040%

    No Known Activations