© 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. 2-RES-JB
    11. 4527
    Prev
    Next
    INDEX
    Explanations

    phrases related to the eye or visual perception

    oai_token-act-pair · gpt-3.5-turbo

    references to "Eye" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.72
    izational
    -0.69
    ulative
    -0.68
    Yan
    -0.68
    umbling
    -0.66
    channelAvailability
    -0.63
    itative
    -0.63
    liga
    -0.63
    agically
    -0.63
    cha
    -0.62
    POSITIVE LOGITS
     sockets
    0.95
     Eyes
    0.93
     Eye
    0.83
    Eye
    0.78
    BSD
    0.76
     teeth
    0.75
    ewitness
    0.75
    eyed
    0.75
     cheeks
    0.71
    beam
    0.70
    Activations Density 0.008%

    No Known Activations