© 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. 9142
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations and projects

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the concept of "eds."

    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
    TY
    -0.84
    MENT
    -0.73
    asso
    -0.71
    TE
    -0.68
    MENTS
    -0.65
    UTE
    -0.63
    rene
    -0.61
    mented
    -0.61
    izoph
    -0.61
    framework
    -0.61
    POSITIVE LOGITS
    nesday
    1.08
    eds
    0.99
    kins
    0.97
    terday
    0.94
    linger
    0.90
    onian
    0.85
    pace
    0.80
    emption
    0.78
    dale
    0.77
    lings
    0.77
    Activations Density 0.011%

    No Known Activations