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. 10-RES-JB
    6. 15144
    Prev
    Next
    INDEX
    Explanations

    the word "rein" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rein" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thumbnail
    -0.74
     reluct
    -0.72
    theless
    -0.67
     overheard
    -0.65
     Leilan
    -0.65
     funer
    -0.63
     miscarriage
    -0.62
     newsletters
    -0.61
     twins
    -0.60
     Akin
    -0.60
    POSITIVE LOGITS
    vention
    1.68
    statement
    1.51
    itialized
    1.40
    stall
    1.36
    ventions
    1.29
    vent
    1.19
    itial
    1.19
    vision
    1.17
    jected
    1.10
    v
    1.10
    Activations Density 0.025%

    No Known Activations