© 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. 11-RES-JB
    11. 7003
    Prev
    Next
    INDEX
    Explanations

    words related to academic disciplines and professions, particularly those in the fields of research, security, and communication

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academic disciplines and professional fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Races
    -0.75
     Churches
    -0.71
    interstitial
    -0.70
     Shades
    -0.69
     Soldiers
    -0.69
     Shattered
    -0.67
     Enemies
    -0.65
     UNITED
    -0.65
    skirts
    -0.65
     Mandatory
    -0.65
    POSITIVE LOGITS
     analyst
    1.48
     strategist
    1.41
     consultant
    1.36
     advisor
    1.36
     planner
    1.36
     engineer
    1.36
     specialist
    1.35
     expert
    1.33
     professor
    1.32
     researcher
    1.31
    Activations Density 0.168%

    No Known Activations