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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12490
    Prev
    Next
    INDEX
    Explanations

    descriptions of dark or silent environments

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to environmental conditions and personal experiences in challenging weather

    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
     Registry
    -0.76
    IGN
    -0.73
    universal
    -0.72
     Cosponsors
    -0.72
    igen
    -0.71
    ularity
    -0.71
     Upgrade
    -0.70
     Collabor
    -0.70
    anton
    -0.70
     copied
    -0.70
    POSITIVE LOGITS
     humidity
    1.69
     temperatures
    1.60
     mosquitoes
    1.59
     rain
    1.58
     mosquit
    1.55
     rains
    1.52
     sunlight
    1.47
     rainy
    1.46
     raining
    1.46
     rainfall
    1.42
    Activations Density 0.594%

    No Known Activations