© 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. 6-RES-JB
    11. 16890
    Prev
    Next
    INDEX
    Explanations

    countries and states

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or nationalities

    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
    hedon
    -0.79
    VALUE
    -0.76
    xual
    -0.75
    ocracy
    -0.74
    ldom
    -0.74
    ãĤ¦ãĤ¹
    -0.71
    roma
    -0.71
    herer
    -0.71
    udder
    -0.71
    enment
    -0.70
    POSITIVE LOGITS
     lawmaker
    1.09
     lawmakers
    0.88
     senator
    0.88
     congressman
    0.87
     bureau
    0.85
     authorities
    0.83
     legislator
    0.82
     prosecutors
    0.80
     Deputy
    0.80
     businessman
    0.79
    Activations Density 0.328%

    No Known Activations