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. 13612
    Prev
    Next
    INDEX
    Explanations

    geographical locations or proper nouns related to the Bahamas

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bahá'í faith and its associated terms

    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
    enegger
    -0.66
     litter
    -0.63
    anwhile
    -0.62
    chnology
    -0.61
    guard
    -0.60
    apers
    -0.60
    essee
    -0.59
    é¾įå¥ij士
    -0.59
     guardians
    -0.59
     blank
    -0.58
    POSITIVE LOGITS
    renheit
    1.08
    asa
    0.93
    aii
    0.87
    reath
    0.86
    aha
    0.84
    idd
    0.84
    ·
    0.84
    ´
    0.84
    anas
    0.83
    ani
    0.82
    Activations Density 0.009%

    No Known Activations