© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16224
    Prev
    Next
    INDEX
    Explanations

    emotional and evaluative language such as expressions of sadness, unfairness, and overwhelming feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness or feelings of unfairness

    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
     metic
    -0.65
     concess
    -0.62
     toured
    -0.62
     meticulous
    -0.61
     contracted
    -0.60
     confiscated
    -0.57
     Moroc
    -0.57
     excel
    -0.56
     suspected
    -0.56
     kios
    -0.56
    POSITIVE LOGITS
    âĢ
    1.54
    âĺ
    1.30
    [/
    1.26
    !!!!
    1.26
    </
    1.20
    !!
    1.19
     ðŁij
    1.18
    âľ
    1.18
    ãĢ
    1.17
    âĿ
    1.17
    Activations Density 0.683%

    No Known Activations