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. 2-RES-JB
    6. 22649
    Prev
    Next
    INDEX
    Explanations

    the word "Rufus"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Rufus."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Siren
    -0.71
     Carmen
    -0.69
     Means
    -0.63
     Neutral
    -0.63
     Rift
    -0.63
    xual
    -0.62
    Publisher
    -0.61
     Clash
    -0.60
     Reign
    -0.59
    ngth
    -0.59
    POSITIVE LOGITS
    uf
    1.10
    eatures
    0.93
    req
    0.90
    edd
    0.88
    ortun
    0.85
    igi
    0.83
    uitous
    0.83
    ixt
    0.81
    reys
    0.80
    ranch
    0.79
    Activations Density 0.008%

    No Known Activations