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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21007
    Prev
    Next
    INDEX
    Explanations

    conjunctions like "and," "but," and "or" alongside verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conjunction or relationship between actions and intentions

    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
    thought
    -0.69
    rored
    -0.64
    riad
    -0.63
    icol
    -0.61
    awed
    -0.59
    Morning
    -0.59
    natureconservancy
    -0.58
    Lens
    -0.57
    krit
    -0.57
    cloth
    -0.56
    POSITIVE LOGITS
     to
    1.24
     ensure
    1.19
     achieve
    1.17
     maximize
    1.17
     facilitate
    1.17
     satisfy
    1.16
     preserve
    1.16
     minimize
    1.15
     promote
    1.14
     establish
    1.14
    Activations Density 0.452%

    No Known Activations