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. 4-RES-JB
    6. 7759
    Prev
    Next
    INDEX
    Explanations

    phrases containing specific abbreviations 'ac' followed by a number related to academic or medical references

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "ac-" which often relate to acceleration or academic concepts

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

    No Comments

    Negative Logits
    vous
    -0.94
    ĸļ
    -0.75
    hof
    -0.74
     Dare
    -0.71
     Stur
    -0.70
    wich
    -0.67
    eker
    -0.66
     Burk
    -0.66
     Kuh
    -0.66
     Huckabee
    -0.66
    POSITIVE LOGITS
    rylic
    1.16
    oustic
    1.14
    celer
    1.06
    ademic
    1.01
    emia
    0.92
    emies
    0.89
    ric
    0.89
    atech
    0.88
    upuncture
    0.88
    acia
    0.87
    Activations Density 0.020%

    No Known Activations