© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14867
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuity or continuation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "continue" and its variations

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

    No Comments

    Negative Logits
    */(
    -0.77
    acho
    -0.73
    ħĭ
    -0.73
    Reviewer
    -0.69
    eah
    -0.65
     puppies
    -0.64
    houses
    -0.64
    footed
    -0.64
    feet
    -0.63
    ilded
    -0.63
    POSITIVE LOGITS
    uation
    1.14
    uously
    1.09
    uations
    1.08
    uity
    1.05
    uum
    0.99
    contin
    0.91
     Contin
    0.90
    uality
    0.90
    uous
    0.87
    ually
    0.86
    Activations Density 0.006%

    No Known Activations