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. 23196
    Prev
    Next
    INDEX
    Explanations

    phrases related to opposition or resistance

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons or contrasts, particularly involving the term "against."

    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
    ffe
    -0.79
    ornia
    -0.74
    Ut
    -0.72
    shire
    -0.72
    CTV
    -0.69
    redo
    -0.66
    ocument
    -0.66
    ayette
    -0.66
    milo
    -0.65
    enough
    -0.65
    POSITIVE LOGITS
     backdrop
    1.58
     onslaught
    0.82
     odds
    0.80
     wall
    0.77
     evils
    0.77
     invaders
    0.77
     enemy
    0.77
     presumption
    0.76
     intruder
    0.75
     temptation
    0.74
    Activations Density 0.220%

    No Known Activations