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. 6-RES-JB
    6. 6127
    Prev
    Next
    INDEX
    Explanations

    approximate numerical values

    oai_token-act-pair · gpt-3.5-turbo

    the term "approximately" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ters
    -0.84
    woods
    -0.81
    TB
    -0.73
    era
    -0.71
    gers
    -0.69
    enders
    -0.68
    ny
    -0.66
    lers
    -0.66
    lins
    -0.65
    neys
    -0.65
    POSITIVE LOGITS
    PsyNetMessage
    0.77
     analogous
    0.76
     200
    0.75
     Approximately
    0.74
     820
    0.73
     midway
    0.72
    atility
    0.72
     800
    0.72
     contempor
    0.72
     approximate
    0.72
    Activations Density 0.021%

    No Known Activations