© 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. 6297
    Prev
    Next
    INDEX
    Explanations

    locations or geographical entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations and names

    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
    worms
    -0.80
    IFE
    -0.78
    ingly
    -0.76
    sb
    -0.76
    eat
    -0.74
    ding
    -0.72
    fast
    -0.72
    ded
    -0.71
    yrinth
    -0.71
    Cause
    -0.71
    POSITIVE LOGITS
    asus
    0.92
    utical
    0.88
    folios
    0.84
     Papua
    0.84
    ograms
    0.77
    ogram
    0.75
    ocry
    0.74
     Por
    0.74
    etary
    0.73
    roleum
    0.72
    Activations Density 0.027%

    No Known Activations