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. 8-RES-JB
    6. 9518
    Prev
    Next
    INDEX
    Explanations

    information about reading or continuing reading a main story from an advertisement or newsletter

    oai_token-act-pair · gpt-3.5-turbo

    the act of continuing to read

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.79
     Gleaming
    -0.73
    footed
    -0.65
    ignt
    -0.65
     Profession
    -0.62
    icion
    -0.61
    owl
    -0.61
    phies
    -0.60
    folk
    -0.60
    è¦ļéĨĴ
    -0.59
    POSITIVE LOGITS
     isEnabled
    0.70
     Below
    0.69
    ...]
    0.64
     âĨĴ
    0.62
     ARTICLE
    0.62
     POLITICO
    0.62
     toggle
    0.61
     aloud
    0.60
     limbo
    0.59
     BELOW
    0.59
    Activations Density 0.016%

    No Known Activations