© 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. 9-RES-JB
    11. 5263
    Prev
    Next
    INDEX
    Explanations

    pronouns 'They' or 'It' at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to subjects in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGTON
    -0.69
    interstitial
    -0.67
     dstg
    -0.66
    Offline
    -0.60
    HAM
    -0.59
    EngineDebug
    -0.59
     Rebellion
    -0.58
     bothering
    -0.57
     Pep
    -0.55
    natureconservancy
    -0.55
    POSITIVE LOGITS
     also
    1.45
     furthermore
    1.35
    also
    1.18
     therefore
    1.17
     moreover
    1.13
     additionally
    1.12
     then
    1.01
     likewise
    0.99
     thus
    0.97
     consequently
    0.95
    Activations Density 0.336%

    No Known Activations