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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 15978
    Prev
    Next
    INDEX
    Explanations

    names of companies and organizations

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding the existence or characteristics of entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jog
    -0.78
     heights
    -0.76
     IMAGES
    -0.73
    owan
    -0.73
     heavens
    -0.72
     stroke
    -0.71
    rouse
    -0.70
    pered
    -0.70
     Temper
    -0.69
     glances
    -0.68
    POSITIVE LOGITS
     headquartered
    1.53
     sponsoring
    1.39
     suing
    1.23
     conducting
    1.21
     partnering
    1.19
     investigating
    1.15
     supplying
    1.14
     cooperating
    1.13
     obligated
    1.11
     responsible
    1.10
    Activations Density 0.278%

    No Known Activations