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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20979
    Prev
    Next
    INDEX
    Explanations

    instances where the subject is "thinking" or considering something

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal thoughts or experiences

    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
    adra
    -0.71
    mma
    -0.68
    >>\
    -0.68
     Nanto
    -0.66
    610
    -0.65
    è¦ļéĨĴ
    -0.64
     Regions
    -0.63
    021
    -0.63
    mentioned
    -0.62
    70710
    -0.61
    POSITIVE LOGITS
     invincible
    0.79
     unbeat
    0.75
     harmless
    0.68
     joking
    0.66
     Bout
    0.65
     innocuous
    0.63
     safest
    0.63
     immune
    0.62
     kindred
    0.61
     Rack
    0.61
    Activations Density 0.179%

    No Known Activations