© 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. 10-RES-JB
    11. 3248
    Prev
    Next
    INDEX
    Explanations

    phrases related to endorsements or approval

    oai_token-act-pair · gpt-3.5-turbo

    repeated usage of the definite article "the" in various contexts

    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
     suppose
    -0.91
    SPONSORED
    -0.82
    ãĥĺ
    -0.76
     dunno
    -0.76
    acid
    -0.74
     reckoned
    -0.74
     apiece
    -0.72
    etime
    -0.70
    pless
    -0.70
    iser
    -0.70
    POSITIVE LOGITS
     Comprehensive
    1.10
     Committee
    1.04
     Department
    1.04
     Advisory
    1.00
     foregoing
    0.99
     Subcommittee
    0.98
     Commission
    0.93
     Administration
    0.92
     Partnership
    0.92
     importance
    0.91
    Activations Density 0.370%

    No Known Activations