© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6993
    Prev
    Next
    INDEX
    Explanations

    geographical locations, specifically focusing on regions and countries

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and their market-related data

    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
     bulldo
    -0.89
     glim
    -0.68
     archaeologists
    -0.67
     archae
    -0.65
     poet
    -0.64
     demol
    -0.64
     Rebell
    -0.64
     bicycl
    -0.64
     demolition
    -0.63
     Bundy
    -0.63
    POSITIVE LOGITS
     Asia
    1.46
     Europe
    1.46
     countries
    1.41
     Countries
    1.35
     UK
    1.35
     Netherlands
    1.33
     Philippines
    1.31
    Australia
    1.30
     Australia
    1.29
     Japan
    1.28
    Activations Density 0.318%

    No Known Activations