© 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. 9-RES-JB
    6. 10158
    Prev
    Next
    INDEX
    Explanations

    image credits in text documents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to image credits and attributions

    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
    Tokens
    -0.75
    ailability
    -0.66
     segreg
    -0.66
    iqueness
    -0.66
    resistant
    -0.65
    igmat
    -0.65
    pected
    -0.64
     tyres
    -0.64
     wards
    -0.63
    ãĤ¦ãĤ¹
    -0.62
    POSITIVE LOGITS
     Shutterstock
    1.01
     ©
    0.81
     Provided
    0.75
     Wikimedia
    0.75
     Flickr
    0.74
     CNBC
    0.73
     Uriel
    0.72
     Pavel
    0.72
     YouTube
    0.71
    EDIT
    0.71
    Activations Density 0.034%

    No Known Activations