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. 8304
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "earlier" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "earlier" in various contexts

    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
    odor
    -0.67
    lua
    -0.64
    ocracy
    -0.61
     Religion
    -0.61
     Bolt
    -0.60
     Anthrop
    -0.60
    alion
    -0.60
    Pros
    -0.60
    Hub
    -0.59
    efe
    -0.59
    POSITIVE LOGITS
     generations
    0.94
     versions
    0.93
     stages
    0.90
    noon
    0.88
    foundland
    0.87
    etheless
    0.84
     iterations
    0.81
    than
    0.80
     installments
    0.79
    iations
    0.79
    Activations Density 0.033%

    No Known Activations