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. 3-RES-JB
    6. 14971
    Prev
    Next
    INDEX
    Explanations

    information related to scientific research studies, such as MRI scans, cognitive effects, and specific medical conditions like biotin deficiency

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health and medical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Contract
    -0.79
    raid
    -0.77
    Forge
    -0.75
    wan
    -0.71
    oat
    -0.70
    Unity
    -0.70
    anners
    -0.69
    ulhu
    -0.68
    claimed
    -0.68
    lua
    -0.66
    POSITIVE LOGITS
    âĢIJ
    0.91
     phenotype
    0.78
     âμ
    0.77
     lect
    0.76
     Autism
    0.75
     clinical
    0.74
     therapeutic
    0.73
     medicinal
    0.72
     dietary
    0.71
     quantitative
    0.71
    Activations Density 0.887%

    No Known Activations