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. 11-RES-JB
    6. 19533
    Prev
    Next
    INDEX
    Explanations

    names of individuals starting with the letter 'M'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of celebrity names or notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.65
     Pradesh
    -0.58
    HOME
    -0.57
     kittens
    -0.55
     depend
    -0.55
     verse
    -0.55
     orphans
    -0.55
     Reincarnated
    -0.54
    ï¸
    -0.53
     Sidney
    -0.53
    POSITIVE LOGITS
    ĸļ
    0.73
    arella
    0.70
    uku
    0.66
    clud
    0.66
    ogl
    0.63
    ãĤ±
    0.62
    effects
    0.61
    budget
    0.61
    zen
    0.60
    owicz
    0.60
    Activations Density 0.082%

    No Known Activations