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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 6397
    Prev
    Next
    INDEX
    Explanations

    phrases indicating periodicity

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "Every."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presumably
    -0.63
     apparently
    -0.63
    ile
    -0.62
     conjecture
    -0.60
     affili
    -0.59
    us
    -0.58
     hypothes
    -0.57
     subsequently
    -0.57
     partially
    -0.57
     preliminary
    -0.56
    POSITIVE LOGITS
     Every
    3.06
    Every
    2.32
    every
    2.12
     Each
    1.97
     Whenever
    1.81
     Everyone
    1.69
     every
    1.68
     EVERY
    1.66
     Everyday
    1.63
     Everything
    1.62
    Activations Density 0.017%

    No Known Activations