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. 1-RES-JB
    6. 9779
    Prev
    Next
    INDEX
    Explanations

    terms related to separatism and independence movements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to separatist movements and secession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.98
    eon
    -0.90
    mone
    -0.80
    ITNESS
    -0.80
    Meat
    -0.75
    Guard
    -0.74
     Sent
    -0.73
    Wheel
    -0.73
    Imm
    -0.72
     Oaks
    -0.71
    POSITIVE LOGITS
     separatists
    1.44
     separatist
    1.30
     separat
    1.10
    ignt
    1.02
     secession
    0.97
     strugg
    0.94
     challeng
    0.94
    yip
    0.92
     insurgency
    0.86
     guiActiveUn
    0.86
    Activations Density 0.007%

    No Known Activations