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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 734
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "eye" and related terms or expressions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the eye and its attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emonium
    -0.78
    Published
    -0.76
     Violent
    -0.74
    REDACTED
    -0.71
    WER
    -0.70
    Acknowled
    -0.70
     Bundy
    -0.70
    channelAvailability
    -0.66
    _-
    -0.66
     Meier
    -0.66
    POSITIVE LOGITS
     sockets
    1.31
     socket
    1.03
     lobe
    0.97
    eyed
    0.89
    bones
    0.88
    socket
    0.86
     brow
    0.84
     eye
    0.83
    ight
    0.83
     gou
    0.82
    Activations Density 0.020%

    No Known Activations