© 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. 22195
    Prev
    Next
    INDEX
    Explanations

    proper nouns of named entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "named."

    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
    ende
    -0.71
    arta
    -0.65
    aples
    -0.63
    maxwell
    -0.61
    pel
    -0.61
    atten
    -0.61
    rooms
    -0.61
    vale
    -0.61
    asonry
    -0.60
    ÄŁ
    -0.60
    POSITIVE LOGITS
     named
    3.67
    named
    2.50
     Named
    2.34
     nicknamed
    1.85
     renamed
    1.83
     naming
    1.71
     dubbed
    1.58
     called
    1.53
     titled
    1.51
     names
    1.41
    Activations Density 0.020%

    No Known Activations