Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22778
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a repeated action or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "once again" indicating repetition or recurrence of events

    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
    ription
    -0.77
    eways
    -0.77
    ogether
    -0.75
    dinand
    -0.74
    roximately
    -0.71
    riage
    -0.70
    Exit
    -0.69
     otherwise
    -0.68
    owsky
    -0.67
    other
    -0.66
    POSITIVE LOGITS
     proving
    0.78
     illustrating
    0.75
     demonstrated
    0.72
     reminding
    0.68
     demonstrating
    0.66
    tin
    0.66
     showcased
    0.66
     showcasing
    0.65
     proves
    0.65
     defied
    0.63
    Activations Density 0.035%

    No Known Activations