Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20182
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly regions and countries

    oai_token-act-pair · gpt-3.5-turbo

    references to Latin American and Asian regions or cultures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bats
    -0.87
    mercial
    -0.84
    pload
    -0.82
    wik
    -0.80
    PASS
    -0.79
    isSpecialOrderable
    -0.78
    FOX
    -0.77
    cloud
    -0.75
    VERTISEMENT
    -0.74
    soType
    -0.74
    POSITIVE LOGITS
     dictators
    1.00
    istan
    1.00
     countries
    0.99
     nations
    0.93
     regimes
    0.88
     Economic
    0.81
     civilisation
    0.81
     peoples
    0.80
     Emir
    0.79
     descent
    0.79
    Activations Density 0.049%

    No Known Activations