© 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. 9-RES-JB
    11. 5212
    Prev
    Next
    INDEX
    Explanations

    specific types of data formats used in content, such as lists, rankings, and figures

    oai_token-act-pair · gpt-3.5-turbo
    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
     interf
    -0.86
     reconnect
    -0.83
     evangel
    -0.82
     tink
    -0.81
     rejuven
    -0.80
     antit
    -0.80
     existential
    -0.80
     epist
    -0.79
     apolog
    -0.77
     lect
    -0.75
    POSITIVE LOGITS
    Percent
    1.46
    Rank
    1.45
    Average
    1.38
    verages
    1.31
     Percentage
    1.22
    Year
    1.22
    Total
    1.20
     Average
    1.19
    Country
    1.19
    Chart
    1.17
    Activations Density 0.290%

    No Known Activations