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. 11-RES-JB
    6. 19719
    Prev
    Next
    INDEX
    Explanations

    phrases where the text mentions that no one is involved or responsible

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "no one" and its variations, indicating a focus on themes of isolation, neglect, or lack of attention to issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Launch
    -0.61
     Rounds
    -0.59
     Contin
    -0.59
    qqa
    -0.58
    rn
    -0.58
    ciation
    -0.57
    lihood
    -0.57
    pread
    -0.56
    edged
    -0.56
    hip
    -0.55
    POSITIVE LOGITS
    xious
    1.18
     matter
    1.14
    one
    1.08
     sane
    1.07
     one
    1.05
     amount
    0.96
     longer
    0.93
     sooner
    0.88
     doubt
    0.87
     reputable
    0.87
    Activations Density 0.067%

    No Known Activations