© 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. 11515
    Prev
    Next
    INDEX
    Explanations

    adjectives used to describe eyes

    oai_token-act-pair · gpt-3.5-turbo

    references to "eyes" 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
    urb
    -0.75
    regate
    -0.70
    rent
    -0.70
    fre
    -0.67
    assi
    -0.66
    iversity
    -0.63
    oit
    -0.62
     Mobil
    -0.62
    ional
    -0.61
    è¦ļéĨĴ
    -0.61
    POSITIVE LOGITS
     eyes
    3.91
     Eyes
    2.37
     eye
    2.35
    eyes
    2.30
     ears
    2.10
     eyeb
    1.88
     gaze
    1.85
     eyel
    1.80
     mouths
    1.69
     jaws
    1.69
    Activations Density 0.008%

    No Known Activations