© 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. 7-RES-JB
    11. 3145
    Prev
    Next
    INDEX
    Explanations

    descriptions of events or observations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.77
     ga
    -0.68
    AMP
    -0.63
    ãĥĺ
    -0.63
    gie
    -0.62
    Ïī
    -0.62
    OPA
    -0.62
    iasis
    -0.61
    venge
    -0.61
    TAG
    -0.60
    POSITIVE LOGITS
     suggests
    1.10
     indicates
    1.08
     ensued
    0.97
     confirms
    0.97
     showed
    0.94
     indicated
    0.93
     indicate
    0.90
     suggest
    0.89
     revealed
    0.87
    reports
    0.86
    Activations Density 0.297%

    No Known Activations