© 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. 6768
    Prev
    Next
    INDEX
    Explanations

    technical terms or proper nouns like codes or names that start with "Orig"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Orig" 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
     WATCHED
    -0.77
     Karn
    -0.71
    ute
    -0.69
     Nieto
    -0.68
     Vaughn
    -0.66
    cock
    -0.65
    ticket
    -0.65
     guard
    -0.64
     Weld
    -0.64
     swarm
    -0.62
    POSITIVE LOGITS
    orig
    3.82
    Orig
    3.40
     Orig
    3.04
     orig
    2.70
     ORIG
    1.91
     Origins
    1.53
    origin
    1.50
    Origin
    1.45
     origin
    1.39
     origins
    1.32
    Activations Density 0.028%

    No Known Activations