© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1933
    Prev
    Next
    INDEX
    Explanations

    technical product specifications and descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific product models or types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.80
    Policy
    -0.80
    Politics
    -0.79
    ulty
    -0.79
    Companies
    -0.76
    ictions
    -0.75
     behavi
    -0.74
    NetMessage
    -0.74
    istry
    -0.74
    anwhile
    -0.72
    POSITIVE LOGITS
     stainless
    1.25
     aluminum
    1.16
     Aluminum
    1.08
     Stainless
    1.04
     convertible
    1.03
     Deluxe
    0.99
     sedan
    0.97
     sized
    0.96
     steel
    0.93
     oval
    0.92
    Activations Density 0.832%

    No Known Activations