© 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. 0-RES-JB
    11. 1220
    Prev
    Next
    INDEX
    Explanations

    the word "Again"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "Again."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     current
    -0.66
     recent
    -0.65
     minimum
    -0.64
     nick
    -0.63
     thousands
    -0.61
     handic
    -0.60
     opinion
    -0.60
     enactment
    -0.59
     average
    -0.58
     exclusive
    -0.58
    POSITIVE LOGITS
     Again
    3.74
    Again
    2.92
    again
    2.43
     again
    2.04
     Lastly
    1.54
     Finally
    1.49
     AGA
    1.47
    Finally
    1.43
     Twice
    1.28
    Lastly
    1.27
    Activations Density 0.019%

    No Known Activations