© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 10667
    Prev
    Next
    INDEX
    Explanations

    years written in specific formats

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and percentages, particularly in a historical or statistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ping
    -0.93
     RELE
    -0.85
     Bray
    -0.84
     rele
    -0.81
     ping
    -0.81
     Kro
    -0.79
     Phi
    -0.76
     phyl
    -0.76
    ray
    -0.76
     Gy
    -0.75
    POSITIVE LOGITS
    80
    1.39
     80
    1.33
    81
    1.28
     81
    1.28
     1983
    1.19
    82
    1.18
     79
    1.17
     1981
    1.17
    79
    1.13
     1980
    1.12
    Activations Density 0.254%

    No Known Activations