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. 3-RES-JB
    6. 1235
    Prev
    Next
    INDEX
    Explanations

    phrases related to political institutions, specifically mentioning the word "parliament."

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bodies or parliaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¦
    -0.69
     Kear
    -0.67
     Stun
    -0.66
    CONT
    -0.66
     Squirrel
    -0.65
     Quant
    -0.63
     Mankind
    -0.63
     Stri
    -0.62
    âķIJâķIJ
    -0.62
     Scouting
    -0.61
    POSITIVE LOGITS
    arians
    1.33
    arian
    1.04
     parliament
    1.03
    ional
    0.88
    arily
    0.82
    icians
    0.82
    liament
    0.81
    abulary
    0.81
     cens
    0.81
    ileaks
    0.79
    Activations Density 0.013%

    No Known Activations