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. 23221
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word 'like'

    oai_token-act-pair · gpt-3.5-turbo

    the word "like" used in comparisons or similarities

    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
     enthusi
    -0.80
    ape
    -0.75
    Americ
    -0.74
    tein
    -0.70
    ennes
    -0.70
    dies
    -0.69
    duction
    -0.67
    hiba
    -0.66
    duct
    -0.65
    aley
    -0.65
    POSITIVE LOGITS
    lihood
    1.76
    liest
    1.26
    lier
    1.22
    liness
    0.97
    minded
    0.91
     clock
    0.77
     minded
    0.73
    ly
    0.73
     ours
    0.69
     wildfire
    0.64
    Activations Density 0.044%

    No Known Activations