© 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. 9-RES-JB
    11. 9933
    Prev
    Next
    INDEX
    Explanations

    specific locations or addresses

    oai_token-act-pair · gpt-3.5-turbo

    specific addresses and location descriptions

    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
     rehe
    -0.76
    NPR
    -0.67
     unheard
    -0.66
    lessness
    -0.66
     hiber
    -0.66
     autobiography
    -0.65
    Japan
    -0.65
     organising
    -0.64
     homebrew
    -0.63
     unmatched
    -0.63
    POSITIVE LOGITS
     Avenue
    1.70
     Blvd
    1.63
     Boulevard
    1.55
     Ave
    1.55
     Rd
    1.50
     Street
    1.49
     Highway
    1.37
     Road
    1.36
     avenue
    1.36
     Drive
    1.30
    Activations Density 0.216%

    No Known Activations