© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 9615
    Prev
    Next
    INDEX
    Explanations

    comparative or quantitative terms like "relative."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eret
    -0.85
    enegger
    -0.84
    spr
    -0.83
    ERG
    -0.83
    schild
    -0.81
    tein
    -0.81
    storm
    -0.79
    otle
    -0.77
    alon
    -0.76
    alos
    -0.76
    POSITIVE LOGITS
     humidity
    1.09
     ease
    0.84
     abund
    0.82
     newcomer
    0.82
     pronoun
    0.78
     importance
    0.78
     inexper
    0.78
     merits
    0.77
     anonymity
    0.77
    ability
    0.77
    Activations Density 0.031%

    No Known Activations