© 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. 8-RES-JB
    11. 7105
    Prev
    Next
    INDEX
    Explanations

    pronouns 'they' paired with verbs indicating actions or states

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the pronoun "they."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eps
    -0.77
     Cumber
    -0.70
     Courier
    -0.66
     Vine
    -0.63
     Hunting
    -0.62
     Cobb
    -0.62
     Burg
    -0.62
     Wol
    -0.62
     Phi
    -0.62
     Vog
    -0.62
    POSITIVE LOGITS
    've
    1.18
    'd
    1.16
    're
    1.09
    selves
    0.97
    zbollah
    0.88
     appre
    0.88
    'll
    0.88
     tasted
    0.87
     encount
    0.87
     disapprove
    0.85
    Activations Density 0.078%

    No Known Activations