© 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. 4-RES-JB
    11. 6900
    Prev
    Next
    INDEX
    Explanations

    references to the protein keratin, including names and related terms

    oai_token-act-pair · gpt-3.5-turbo

    words and suffixes related to materials and substances, particularly those associated with biological components

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

    No Comments

    Negative Logits
    enance
    -0.73
    ŀ
    -0.69
     XY
    -0.67
     Seym
    -0.67
    lying
    -0.67
    aeper
    -0.66
    Trend
    -0.66
     Nest
    -0.66
     Wife
    -0.66
    Ü
    -0.65
    POSITIVE LOGITS
    strument
    1.15
    ned
    1.11
    ners
    1.11
    ny
    1.05
    osaurs
    1.04
    iti
    1.01
    ergic
    0.94
    atin
    0.94
    jury
    0.93
    ning
    0.90
    Activations Density 0.023%

    No Known Activations