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. 10-RES-JB
    6. 67
    Prev
    Next
    INDEX
    Explanations

    numerals and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to sections or parts of a text or website

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nt
    -0.54
     ruining
    -0.53
     worthless
    -0.52
     didnt
    -0.51
     violation
    -0.50
     rubbish
    -0.50
     rejection
    -0.50
     wont
    -0.48
     useless
    -0.48
     faults
    -0.48
    POSITIVE LOGITS
    alan
    0.62
    å§«
    0.59
    luster
    0.59
    arger
    0.55
    lique
    0.55
    ular
    0.53
    reditary
    0.52
    pherd
    0.50
    atown
    0.49
    ordial
    0.49
    Activations Density 0.692%

    No Known Activations