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. 6-RES-JB
    6. 11200
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing quantity or importance

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that emphasize quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.64
    rongh
    -0.62
    MpServer
    -0.59
    senal
    -0.57
    baugh
    -0.56
    ople
    -0.56
    kefeller
    -0.54
     Himself
    -0.53
    oliath
    -0.52
    ibrary
    -0.52
    POSITIVE LOGITS
    ccording
    0.63
     Regist
    0.59
     Dreams
    0.59
    ATCH
    0.58
    ndra
    0.57
     Foods
    0.56
     Countries
    0.55
     meanwhile
    0.54
     shalt
    0.54
    ortunately
    0.53
    Activations Density 0.283%

    No Known Activations