© 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. 10-RES-JB
    6. 13631
    Prev
    Next
    INDEX
    Explanations

    locations or places described by their proximity to other landmarks or distances

    oai_token-act-pair · gpt-3.5-turbo

    specific geographic locations and distances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.72
    obal
    -0.65
    phrine
    -0.62
     Aliens
    -0.60
     Metatron
    -0.60
     superflu
    -0.59
    zynski
    -0.59
    ombies
    -0.57
    olon
    -0.56
    ahl
    -0.56
    POSITIVE LOGITS
     miles
    1.37
     mile
    1.24
     kilometres
    1.24
     kilometers
    1.14
     east
    1.14
     blocks
    1.13
     south
    1.11
     northwest
    1.10
     north
    1.10
     southeast
    1.09
    Activations Density 0.194%

    No Known Activations