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. 15611
    Prev
    Next
    INDEX
    Explanations

    instances of describing something as emotionally or physically challenging

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to challenges and difficulties

    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
    requires
    -0.82
    pmwiki
    -0.77
    Downloadha
    -0.77
    apons
    -0.67
     warranties
    -0.64
    objects
    -0.64
    Reference
    -0.62
    currently
    -0.62
    iddles
    -0.62
    İĭ
    -0.61
    POSITIVE LOGITS
     initially
    0.90
     timing
    0.80
     culminating
    0.75
     considering
    0.74
     because
    0.74
     for
    0.73
     beforehand
    0.70
     last
    0.70
    actic
    0.69
     originally
    0.69
    Activations Density 0.372%

    No Known Activations