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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21018
    Prev
    Next
    INDEX
    Explanations

    phrases related to the absence or removal of something, often with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "less."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BAT
    -0.77
    BIT
    -0.72
    MAG
    -0.69
    NEWS
    -0.69
    oÄŁ
    -0.69
    aeper
    -0.68
    ERN
    -0.67
    MA
    -0.67
    BU
    -0.67
     Clause
    -0.66
    POSITIVE LOGITS
    edly
    0.89
     autom
    0.76
    hearted
    0.71
     bystand
    0.71
    lihood
    0.67
    icity
    0.67
    uced
    0.66
    itary
    0.66
    enne
    0.64
    theless
    0.63
    Activations Density 0.026%

    No Known Activations