Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16237
    Prev
    Next
    INDEX
    Explanations

    words related to frequency or repetition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate frequency or repetition

    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
    ueller
    -0.63
    miss
    -0.62
    bats
    -0.60
    standing
    -0.58
    endum
    -0.58
     Humanity
    -0.57
     fingert
    -0.56
    Thank
    -0.56
    arl
    -0.56
    final
    -0.55
    POSITIVE LOGITS
     often
    3.33
    often
    2.78
     frequently
    2.59
     seldom
    2.44
     sometimes
    2.42
     usually
    2.37
     rarely
    2.34
     typically
    2.20
    sometimes
    2.19
     Often
    2.14
    Activations Density 0.024%

    No Known Activations