© 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. 9-RES-JB
    11. 15606
    Prev
    Next
    INDEX
    Explanations

    words related to perfection or an ideal state

    oai_token-act-pair · gpt-3.5-turbo

    concepts and discussions surrounding ideals and idealism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bane
    -0.78
    NetMessage
    -0.70
    SEE
    -0.66
    cloth
    -0.65
    words
    -0.64
    bars
    -0.62
    books
    -0.61
    ker
    -0.60
    cano
    -0.60
    Lago
    -0.59
    POSITIVE LOGITS
    istic
    1.54
    istically
    1.39
    ized
    1.22
    ization
    1.15
    ised
    1.13
    isation
    1.08
    izing
    1.04
    izations
    1.03
    imum
    1.00
    ising
    0.99
    Activations Density 0.029%

    No Known Activations