Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23421
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "na" in various contexts

    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
     desk
    -0.73
     Martian
    -0.66
     figure
    -0.65
     Sounders
    -0.62
     interstellar
    -0.60
     heck
    -0.59
     force
    -0.59
     assembled
    -0.59
     JPEG
    -0.57
     bounce
    -0.57
    POSITIVE LOGITS
    na
    4.43
    nas
    2.13
    nah
    1.91
    ni
    1.81
    ne
    1.62
    NA
    1.61
    nan
    1.58
    nes
    1.56
    ny
    1.56
    nia
    1.48
    Activations Density 0.010%

    No Known Activations