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. 3-RES-JB
    6. 10971
    Prev
    Next
    INDEX
    Explanations

    the surname "Stoltenberg"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the substring "ten" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.69
     arous
    -0.69
    gain
    -0.65
     aroused
    -0.64
    cffffcc
    -0.63
     sucker
    -0.63
    head
    -0.62
     simultaneously
    -0.60
     hunger
    -0.59
    istically
    -0.57
    POSITIVE LOGITS
    nis
    1.16
    ney
    1.03
    holm
    0.96
    encing
    0.93
    oyer
    0.92
    acity
    0.88
    stad
    0.88
    bourg
    0.88
    ieth
    0.86
    pai
    0.85
    Activations Density 0.005%

    No Known Activations