© 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. 15590
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or geographic areas

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and their characteristics

    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
     induct
    -0.60
    Prof
    -0.56
     actu
    -0.56
     expr
    -0.56
    rators
    -0.55
    Statement
    -0.55
    TPP
    -0.55
    ONS
    -0.55
    oeuv
    -0.55
    Material
    -0.54
    POSITIVE LOGITS
     southwestern
    1.16
     northeastern
    1.15
     southeastern
    1.15
     rural
    1.14
     southwest
    1.13
     northwest
    1.11
     suburb
    1.11
     countryside
    1.11
     northwestern
    1.11
     northern
    1.09
    Activations Density 0.943%

    No Known Activations