Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21785
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Is" in the text

    oai_token-act-pair · gpt-3.5-turbo

    interrogative statements or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.79
    ãģĮ
    -0.77
    ilight
    -0.70
     stitches
    -0.66
     encounters
    -0.64
     boards
    -0.64
     fins
    -0.63
     straps
    -0.62
     wart
    -0.62
     sails
    -0.61
    POSITIVE LOGITS
    olated
    1.49
    olation
    1.33
    abella
    1.22
    olate
    1.21
    htar
    1.11
    peria
    1.11
    senal
    1.03
    sei
    1.01
    rael
    0.98
    terness
    0.95
    Activations Density 0.065%

    No Known Activations