© 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. 2-RES-JB
    6. 809
    Prev
    Next
    INDEX
    Explanations

    compound words starting with "Anglo" or "Indo."

    oai_token-act-pair · gpt-4-turbo

    terms related to specific cultural or ethnic groups, specifically the Anglo-Saxons and Glaswegian identity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to Anglo-Saxon heritage and language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parables
    -0.90
    */(
    -0.82
    PsyNetMessage
    -0.77
    yrights
    -0.72
    HCR
    -0.71
    ULE
    -0.70
    hips
    -0.69
    apego
    -0.68
    tumblr
    -0.68
    chell
    -0.68
    POSITIVE LOGITS
     Anglo
    0.99
    entimes
    0.84
    ctions
    0.76
    ¬¼
    0.75
     Ang
    0.73
     Druid
    0.71
    Sax
    0.67
    minster
    0.67
     Celt
    0.65
     Klux
    0.64
    Activations Density 0.003%

    No Known Activations