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. 1-RES-JB
    6. 17769
    Prev
    Next
    INDEX
    Explanations

    phrases indicating continuation or persistence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "continue" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usterity
    -0.70
    adish
    -0.70
    idden
    -0.68
    aster
    -0.67
    soc
    -0.65
    typ
    -0.64
    ister
    -0.64
    ummer
    -0.64
    ranch
    -0.64
     Sheikh
    -0.63
    POSITIVE LOGITS
     continued
    0.82
     uninterrupted
    0.81
     repeating
    0.79
     unanswered
    0.78
     unab
    0.78
     ende
    0.76
     continues
    0.75
     reiter
    0.74
     unchanged
    0.74
    Continue
    0.74
    Activations Density 0.026%

    No Known Activations