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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13316
    Prev
    Next
    INDEX
    Explanations

    opinions or actions of others in contrast to a particular viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    references to differing perspectives or opinions

    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
    -+
    -0.74
    "},"
    -0.72
    / 
    -0.67
    ocracy
    -0.66
    Charg
    -0.63
    United
    -0.63
    Registration
    -0.61
    UID
    -0.60
    Alright
    -0.59
    UTC
    -0.59
    POSITIVE LOGITS
     simply
    1.04
     merely
    1.01
     prefer
    0.99
     succumb
    0.90
     aren
    0.88
     are
    0.87
     cling
    0.80
     remain
    0.79
     weren
    0.78
     insist
    0.78
    Activations Density 0.079%

    No Known Activations