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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 275
    Prev
    Next
    INDEX
    Explanations

    the word "entire"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "entire."

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

    No Comments

    Negative Logits
    ju
    -0.74
    asta
    -0.69
    inel
    -0.68
    ker
    -0.67
    zy
    -0.66
    akers
    -0.64
    friends
    -0.64
    ac
    -0.64
    ific
    -0.63
    cl
    -0.62
    POSITIVE LOGITS
    heartedly
    0.89
     entire
    0.77
    ength
    0.75
     contents
    0.75
     entirety
    0.72
     breadth
    0.71
    hearted
    0.71
     length
    0.71
    uania
    0.70
     ordeal
    0.70
    Activations Density 0.021%

    No Known Activations