© 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. 10-RES-JB
    11. 11456
    Prev
    Next
    INDEX
    Explanations

    countries based on their nationality appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to nationalities or ethnic identities

    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
    icago
    -0.83
    uably
    -0.78
    thia
    -0.76
    nels
    -0.75
    days
    -0.74
    sylv
    -0.74
    irrel
    -0.73
    ãĥĺãĥ©
    -0.71
    affles
    -0.71
    bits
    -0.70
    POSITIVE LOGITS
     authorities
    1.15
     parliament
    1.07
     broadcaster
    1.05
     newspaper
    1.04
     lawmaker
    1.04
     regulator
    1.02
     tabloid
    1.02
     politician
    1.00
     government
    0.96
     journalist
    0.95
    Activations Density 0.135%

    No Known Activations