© 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. 6375
    Prev
    Next
    INDEX
    Explanations

    proper nouns that are unveiled or introduced

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unveiled" 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
     situations
    -0.67
     quota
    -0.62
    feed
    -0.60
    gg
    -0.60
     parallel
    -0.60
     gram
    -0.59
    count
    -0.59
     logic
    -0.58
    arg
    -0.58
     value
    -0.58
    POSITIVE LOGITS
     unveiled
    3.20
     unveil
    2.17
     unveiling
    2.11
     unve
    1.83
     announced
    1.54
     revealed
    1.49
     debuted
    1.48
     showcased
    1.44
     introduced
    1.38
     premiered
    1.34
    Activations Density 0.019%

    No Known Activations