© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 808
    Prev
    Next
    INDEX
    Explanations

    terms associated with military equipment and technology

    oai_token-act-pair · gpt-4-turbo

    technical terms related to military equipment and operations

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to military aircraft and weaponry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.80
     Stranger
    -0.77
     Romantic
    -0.75
     Social
    -0.75
    é»Ĵ
    -0.74
     LGBTQ
    -0.73
     LGBT
    -0.73
     Homeless
    -0.72
     Marriage
    -0.72
     Rowling
    -0.72
    POSITIVE LOGITS
     aircraft
    1.17
     propulsion
    1.15
     unmanned
    1.10
     reconnaissance
    1.06
     spacecraft
    1.05
     aboard
    1.04
     capabilities
    1.04
     payload
    1.03
     cargo
    1.03
     submarines
    1.03
    Activations Density 0.715%

    No Known Activations