© 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. 4-RES-JB
    11. 14591
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or denouncement

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "the."

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

    No Comments

    Negative Logits
    Iterator
    -0.76
    elaide
    -0.73
     âĶľâĶĢâĶĢ
    -0.70
    herer
    -0.69
     regulates
    -0.69
    ngth
    -0.68
     Gohan
    -0.66
    âĢij
    -0.66
     denotes
    -0.66
    veland
    -0.65
    POSITIVE LOGITS
     latter
    1.17
     slightest
    1.07
     latest
    1.07
     same
    1.06
    ocratic
    0.97
     notion
    0.95
     idea
    0.95
     Clintons
    0.95
     impending
    0.93
     entire
    0.92
    Activations Density 0.601%

    No Known Activations