© 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. 11612
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or spatial descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to restrictions or intended uses for spaces or objects

    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
    Ĭ±
    -0.86
    intent
    -0.74
    errors
    -0.73
    votes
    -0.72
     pse
    -0.70
    strings
    -0.69
    gex
    -0.68
     warrants
    -0.67
    20439
    -0.66
    oice
    -0.65
    POSITIVE LOGITS
     sanctuary
    1.51
     refuge
    1.35
     lair
    1.34
     residences
    1.33
     paradise
    1.33
     residence
    1.30
     headquarters
    1.24
     workspace
    1.24
     place
    1.20
     havens
    1.20
    Activations Density 0.521%

    No Known Activations