© 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 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. 7-RES-JB
    11. 23528
    Prev
    Next
    INDEX
    Explanations

    instances of the word "several."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "several"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anything
    -0.76
    istan
    -0.69
    IAS
    -0.69
    asta
    -0.67
    urden
    -0.67
    Reviewer
    -0.67
    vest
    -0.66
    ola
    -0.66
    claimer
    -0.66
    NER
    -0.65
    POSITIVE LOGITS
     hundred
    1.67
     thousand
    1.49
     dozen
    1.46
     months
    1.01
    dozen
    1.01
     occasions
    1.00
    teenth
    1.00
     times
    0.99
     weeks
    0.98
     iterations
    0.98
    Activations Density 0.049%

    No Known Activations