© 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. 1-RES-JB
    11. 14168
    Prev
    Next
    INDEX
    Explanations

    words related to the Ionian culture or the Ionian mode in music

    oai_token-act-pair · gpt-3.5-turbo

    words or terms associated with specific nationalities or ethnicities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orative
    -0.83
    raints
    -0.80
     mathemat
    -0.78
    puter
    -0.73
    IRT
    -0.70
    icket
    -0.68
     Ended
    -0.68
    İĭ
    -0.66
    raint
    -0.66
    ãĥīãĥ©
    -0.64
    POSITIVE LOGITS
    ians
    1.11
    ian
    1.02
    nian
    0.95
    ity
    0.93
    apolis
    0.93
    opolis
    0.87
    cies
    0.84
    nis
    0.83
    ocide
    0.82
    ism
    0.79
    Activations Density 0.021%

    No Known Activations