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. 15713
    Prev
    Next
    INDEX
    Explanations

    the phrase "no longer"

    oai_token-act-pair · gpt-3.5-turbo
    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
     Comes
    -0.64
     Takes
    -0.59
     Nanto
    -0.57
    heid
    -0.56
    ousand
    -0.55
    mare
    -0.55
     Converted
    -0.54
     Khe
    -0.53
    ibaba
    -0.53
     Stories
    -0.53
    POSITIVE LOGITS
     longer
    1.63
    xious
    1.21
     doubt
    1.11
    etheless
    1.06
    icably
    0.96
    ct
    0.95
     sooner
    0.93
     LONG
    0.93
    vell
    0.89
    rouse
    0.86
    Activations Density 0.031%

    No Known Activations