© 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. 4-RES-JB
    11. 7296
    Prev
    Next
    INDEX
    Explanations

    words related to height or elevation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to raising or increasing levels, particularly in various contexts

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

    No Comments

    Negative Logits
    Deal
    -0.82
    ãģ®éŃĶ
    -0.81
    vous
    -0.77
    TERN
    -0.75
    deal
    -0.74
    maker
    -0.74
    colo
    -0.72
    fare
    -0.70
    patch
    -0.69
    INESS
    -0.68
    POSITIVE LOGITS
    xual
    1.09
     elev
    1.02
     elevation
    0.97
     elevate
    0.86
     elevated
    0.85
    uations
    0.84
     heights
    0.83
    aution
    0.83
    umatic
    0.76
     Elev
    0.75
    Activations Density 0.028%

    No Known Activations