© 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. 2-RES-JB
    11. 17176
    Prev
    Next
    INDEX
    Explanations

    visual-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to visual elements or aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.80
    renheit
    -0.75
    lot
    -0.72
    isSpecialOrderable
    -0.69
    olid
    -0.67
    kson
    -0.67
    rifice
    -0.65
    KEN
    -0.65
    uddin
    -0.64
    IRO
    -0.64
    POSITIVE LOGITS
    isations
    1.01
    izations
    1.00
    ized
    0.96
     cortex
    0.88
     cues
    0.88
     visual
    0.86
    izer
    0.84
    izable
    0.83
    isable
    0.80
     aids
    0.80
    Activations Density 0.015%

    No Known Activations