© 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. 11-RES-JB
    11. 24160
    Prev
    Next
    INDEX
    Explanations

    proper nouns and organizations related to politics and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.98
    rawdownloadcloneembedreportprint
    -0.88
    Adds
    -0.77
    laughs
    -0.69
     Adds
    -0.69
     Starts
    -0.66
    uces
    -0.64
    Increases
    -0.63
    Allows
    -0.62
     Says
    -0.62
    POSITIVE LOGITS
     were
    1.71
     weren
    1.70
    were
    1.41
     lacked
    1.30
     hadn
    1.30
     had
    1.25
    Were
    1.23
     Were
    1.18
     belonged
    1.14
     aren
    1.13
    Activations Density 0.435%

    No Known Activations