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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 15161
    Prev
    Next
    INDEX
    Explanations

    phrases referring to something causing displeasure or discomfort to a specific group of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a significant or substantial quantity or degree

    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
     passports
    -0.72
     Puzzles
    -0.65
    ©¶æ
    -0.64
     Peaks
    -0.62
    cember
    -0.62
     chairs
    -0.59
     caucuses
    -0.58
    jan
    -0.58
     Amendments
    -0.58
     passport
    -0.58
    POSITIVE LOGITS
    ashtra
    0.81
    rah
    0.78
    needed
    0.71
    lier
    0.71
    icipated
    0.68
    distance
    0.67
    shed
    0.67
    spread
    0.65
    rid
    0.65
    inished
    0.65
    Activations Density 0.115%

    No Known Activations