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. 9-RES-JB
    6. 4535
    Prev
    Next
    INDEX
    Explanations

    various phrases related to ways, perspectives, and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    expressions of judgment or critique regarding arguments or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.71
    haar
    -0.69
    quished
    -0.67
    selected
    -0.61
    erson
    -0.61
    lain
    -0.60
    achus
    -0.59
    hma
    -0.59
    yles
    -0.59
    abella
    -0.57
    POSITIVE LOGITS
     sense
    0.96
     standpoint
    0.94
     terms
    0.86
     nutshell
    0.80
     senses
    0.80
     respects
    0.73
     perspective
    0.72
     ways
    0.71
     Terms
    0.71
     reasons
    0.66
    Activations Density 0.487%

    No Known Activations