© 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. 9-RES-JB
    11. 15546
    Prev
    Next
    INDEX
    Explanations

    adjectives describing size or scale

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or placeholders in text, indicating segments where content might be inserted or described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARB
    -0.82
    METHOD
    -0.77
    ancers
    -0.76
    gemony
    -0.76
    anship
    -0.76
    anwhile
    -0.75
    Sex
    -0.74
    Theme
    -0.73
    utics
    -0.72
    CF
    -0.71
    POSITIVE LOGITS
     chunk
    1.18
     sized
    1.13
     wooden
    1.12
     rectangular
    1.10
     intestine
    1.03
     hole
    1.03
     boulder
    1.03
     rectangle
    1.02
     pile
    1.02
     diameter
    1.01
    Activations Density 0.127%

    No Known Activations