Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16927
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals' names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Name2 in "Name1 and Name2"

    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •L9 resid features following 'and'

    No Comments

    Negative Logits
    milo
    -0.69
    adobe
    -0.68
    / 
    -0.63
     suspic
    -0.59
     *)
    -0.57
    pmwiki
    -0.56
    Environment
    -0.55
     SYSTEM
    -0.55
    resy
    -0.54
    culosis
    -0.54
    POSITIVE LOGITS
     alike
    1.43
     respectively
    1.16
    axter
    0.97
    eele
    0.86
     together
    0.78
     selves
    0.72
    anne
    0.71
    esson
    0.69
     Aven
    0.69
     Streets
    0.69
    Activations Density 0.266%

    No Known Activations