© 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. 10-RES-JB
    11. 12050
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs indicating actions or states of being that follow the pattern "subject + verb."

    oai_token-act-pair · gpt-3.5-turbo
    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
     beforehand
    -0.78
     initially
    -0.77
    ascript
    -0.67
     prior
    -0.63
     Initially
    -0.62
     previous
    -0.59
    oused
    -0.58
    arine
    -0.58
    odor
    -0.58
     predecessor
    -0.57
    POSITIVE LOGITS
    here
    0.88
     reckoning
    0.70
     finally
    0.68
     officially
    0.68
    nir
    0.68
     reality
    0.66
     realize
    0.65
     realise
    0.65
    adays
    0.64
     gotta
    0.64
    Activations Density 0.230%

    No Known Activations