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. 7-RES-JB
    6. 16910
    Prev
    Next
    INDEX
    Explanations

    the name "Susie" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Sus" and its variations

    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
    è¦ļéĨĴ
    -0.88
     forging
    -0.70
     stakes
    -0.69
    hetti
    -0.68
     projecting
    -0.68
    akings
    -0.67
    ingo
    -0.66
     living
    -0.65
     joints
    -0.64
     learning
    -0.64
    POSITIVE LOGITS
    pect
    1.20
    annah
    1.20
    pic
    1.15
    pected
    1.15
    pects
    1.05
    pir
    1.05
    pecting
    1.01
    sex
    0.92
    ethe
    0.90
    eker
    0.89
    Activations Density 0.017%

    No Known Activations