© 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. 2775
    Prev
    Next
    INDEX
    Explanations

    verbs related to meeting or coming together

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "meets."

    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
    ãĤ¶
    -0.68
    asp
    -0.64
    ãĤ¹ãĥĪ
    -0.63
    ãĤ¯
    -0.62
    awn
    -0.58
    usage
    -0.58
    amm
    -0.57
    ****************
    -0.57
    anim
    -0.57
     plural
    -0.57
    POSITIVE LOGITS
     meets
    4.00
     meet
    2.21
    meet
    1.61
     met
    1.57
     Meet
    1.57
     satisfies
    1.44
    Meet
    1.39
     confronts
    1.22
     fulf
    1.20
     qualifies
    1.18
    Activations Density 0.010%

    No Known Activations