© 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. 10-RES-JB
    11. 10737
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal relationships and tributes

    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
    ."[
    -1.06
    .–
    -1.06
    —-
    -1.05
    .�
    -0.99
    --
    -0.99
    .*
    -0.99
    âĢ¦.
    -0.98
     goddamn
    -0.98
    ADVERTISEMENT
    -0.98
    ––
    -0.95
    POSITIVE LOGITS
     £
    1.45
     ageing
    1.39
     Newcastle
    1.38
     Yorkshire
    1.35
     Edinburgh
    1.35
     organisers
    1.34
     Cardiff
    1.32
     Britons
    1.31
     tyre
    1.30
     maths
    1.30
    Activations Density 1.393%

    No Known Activations