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. 18460
    Prev
    Next
    INDEX
    Explanations

    specific unicode characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or symbols

    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
    nesday
    -0.73
    agascar
    -0.69
    hander
    -0.68
    aday
    -0.65
    ifications
    -0.63
     externalToEVAOnly
    -0.62
    swick
    -0.61
    essage
    -0.61
    ativity
    -0.60
    omial
    -0.60
    POSITIVE LOGITS
    Į
    1.99
    Ľ
    1.79
    Ĵ
    1.73
    Ķ
    1.72
    ļ
    1.71
    ĥ
    1.69
    ħ
    1.68
    Ĭ
    1.65
    ½
    1.65
    ©
    1.64
    Activations Density 0.014%

    No Known Activations