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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 22107
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government entities and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossibility
    -0.80
    linger
    -0.80
    ocious
    -0.80
    agonist
    -0.80
    undrum
    -0.75
    ription
    -0.75
    thora
    -0.75
    ...]
    -0.71
    atron
    -0.71
    jen
    -0.70
    POSITIVE LOGITS
     coffers
    1.14
     officials
    1.10
     offices
    1.10
     buildings
    1.05
     employees
    1.05
     agencies
    1.04
     sanctioned
    1.01
     personnel
    0.99
     headquarters
    0.98
     pensions
    0.96
    Activations Density 0.215%

    No Known Activations