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. 6-RES-JB
    6. 13168
    Prev
    Next
    INDEX
    Explanations

    sentences with a sense of uncertainty or various possibilities

    oai_token-act-pair · gpt-3.5-turbo

    sentiments of realization and reflection

    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
    requires
    -0.55
    azo
    -0.53
     ®
    -0.53
    jen
    -0.51
    raf
    -0.50
     Says
    -0.50
     currently
    -0.50
     Adds
    -0.49
    habi
    -0.49
    mite
    -0.49
    POSITIVE LOGITS
     outwe
    0.69
    ranged
    0.64
     beforehand
    0.63
     tended
    0.60
     lacked
    0.60
    izoph
    0.60
    Was
    0.58
     mattered
    0.57
     smelled
    0.57
     enthusi
    0.56
    Activations Density 2.710%

    No Known Activations