© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1720
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental, political, and economic activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and corporate issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ossibility
    -0.86
    ouf
    -0.83
    undrum
    -0.81
    issance
    -0.78
    agame
    -0.75
    lihood
    -0.70
    thora
    -0.69
    ammy
    -0.68
    agonist
    -0.67
    ernaut
    -0.66
    POSITIVE LOGITS
     organizations
    1.28
     establishments
    1.23
     agencies
    1.22
     sites
    1.22
     venues
    1.22
     institutions
    1.18
     departments
    1.17
     contexts
    1.16
     groups
    1.16
     entities
    1.15
    Activations Density 0.490%

    No Known Activations