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. 8145
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or delay in timing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts

    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
    izational
    -0.67
    woman
    -0.62
    ogg
    -0.62
    married
    -0.61
    boxing
    -0.61
    ounces
    -0.61
    updated
    -0.60
     downloaded
    -0.59
    uo
    -0.59
    oslov
    -0.59
    POSITIVE LOGITS
     avoid
    1.49
     conserve
    1.32
     prevent
    1.29
     accommodate
    1.29
     ensure
    1.27
     protect
    1.23
     allow
    1.23
     appease
    1.22
     facilitate
    1.21
     coincide
    1.18
    Activations Density 0.202%

    No Known Activations