© 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. 1485
    Prev
    Next
    INDEX
    Explanations

    phrases related to costs and considerations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cost or expense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     âĵĺ
    -0.66
     Together
    -0.61
     Stir
    -0.56
    xit
    -0.56
     Male
    -0.55
     Quote
    -0.54
    isode
    -0.54
     Fishing
    -0.53
     Female
    -0.53
     Than
    -0.53
    POSITIVE LOGITS
    )</
    0.61
    »
    0.60
     beforehand
    0.59
    ļéĨĴ
    0.58
    !).
    0.57
     hemor
    0.56
    ij
    0.55
     notor
    0.55
     cram
    0.55
     collateral
    0.55
    Activations Density 1.342%

    No Known Activations