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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7990
    Prev
    Next
    INDEX
    Explanations

    the name "Oliver" followed by a number, paying special attention to the cases where the number is 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Oliver."

    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
    mble
    -0.83
    ulhu
    -0.74
    Ħ¢
    -0.70
    hz
    -0.70
    evil
    -0.68
    aspx
    -0.68
    habi
    -0.66
    arching
    -0.65
    swing
    -0.65
    ranking
    -0.64
    POSITIVE LOGITS
     Oliver
    1.09
    sson
    0.85
     Wend
    0.78
     Twist
    0.77
    alia
    0.74
     Liu
    0.73
     rall
    0.73
     Gord
    0.72
     Micha
    0.71
     Klein
    0.69
    Activations Density 0.006%

    No Known Activations