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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19489
    Prev
    Next
    INDEX
    Explanations

    the phrase "first and foremost."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADVERTISEMENT
    -0.78
    ãĤ§
    -0.78
    wake
    -0.73
    76561
    -0.71
    :(
    -0.70
    ONSORED
    -0.68
    IRE
    -0.67
    BIP
    -0.65
     Toast
    -0.64
    speech
    -0.64
    POSITIVE LOGITS
    rogen
    1.04
    rogens
    1.03
     consequently
    0.93
     therefore
    0.90
     foremost
    0.80
     awaited
    0.78
     then
    0.76
     possibly
    0.76
    chard
    0.75
     moreover
    0.74
    Activations Density 0.231%

    No Known Activations