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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2227
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of 'eigenfaces', which are a set of eigenvectors used in face recognition

    oai_token-act-pair · gpt-3.5-turbo

    references to "eigenfaces" and related concepts in facial recognition technology

    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
    umbnail
    -0.75
    Ĥª
    -0.68
    ngth
    -0.64
     Archangel
    -0.64
    cffffcc
    -0.63
    ĵĺ
    -0.62
    jri
    -0.62
     immersion
    -0.61
     earnest
    -0.61
    ODUCT
    -0.60
    POSITIVE LOGITS
    esis
    1.23
    igen
    1.11
    baum
    0.96
    otle
    0.93
    ocide
    0.89
    etics
    0.89
    stadt
    0.87
    hardt
    0.87
    ously
    0.82
    etic
    0.82
    Activations Density 0.010%

    No Known Activations