© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21392
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or organizations, specifically focusing on places like Ireland, India, and Canada

    oai_token-act-pair · gpt-3.5-turbo

    locations and country names in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vana
    -0.81
    plet
    -0.77
    enable
    -0.71
    veyard
    -0.70
    icularly
    -0.70
    iago
    -0.68
    vantage
    -0.66
    rans
    -0.64
    Oracle
    -0.63
    fort
    -0.63
    POSITIVE LOGITS
    ;;;;;;;;;;;;
    0.84
     Foundation
    0.81
     Ltd
    0.80
     (@
    0.74
     Orchestra
    0.73
     Association
    0.70
     Limited
    0.69
     LLP
    0.69
     Board
    0.67
     ([
    0.67
    Activations Density 0.100%

    No Known Activations