© 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. 2-RES-JB
    11. 18566
    Prev
    Next
    INDEX
    Explanations

    mentions of unfamiliarity or lack of experience

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unfamiliar."

    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
    ramid
    -0.91
    aminer
    -0.79
    trak
    -0.78
    reens
    -0.77
    chance
    -0.75
    owder
    -0.74
    rate
    -0.67
    roxy
    -0.67
    raq
    -0.66
    vation
    -0.66
    POSITIVE LOGITS
     unfamiliar
    1.21
    ity
    1.05
    sworth
    0.74
     familiar
    0.73
    ities
    0.72
    iliar
    0.72
     acquaintance
    0.69
     Conan
    0.67
    iqueness
    0.66
    icol
    0.66
    Activations Density 0.013%

    No Known Activations