© 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. 22228
    Prev
    Next
    INDEX
    Explanations

    terms related to exceptionally noteworthy or extraordinary subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "remarkable" and its variations

    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
    /
    -0.76
     /
    -0.74
    ink
    -0.68
     vs
    -0.67
     ASAP
    -0.65
    uler
    -0.64
    izer
    -0.64
     anyways
    -0.63
    ache
    -0.63
    queue
    -0.63
    POSITIVE LOGITS
     remarkable
    3.12
     astonishing
    2.24
     extraordinary
    2.22
     astounding
    2.13
     miraculous
    1.94
     remarkably
    1.92
     incredible
    1.88
     startling
    1.87
     admirable
    1.80
     amazing
    1.79
    Activations Density 0.019%

    No Known Activations