© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 1817
    Prev
    Next
    INDEX
    Explanations

    words related to exceptional talent or skill

    oai_token-act-pair · gpt-3.5-turbo

    terms related to giftedness and talent

    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
     Layer
    -0.71
    ERA
    -0.65
     STAND
    -0.64
    EVA
    -0.64
     Uniform
    -0.63
    adish
    -0.60
    MAC
    -0.60
     GEAR
    -0.59
     Ult
    -0.59
    VA
    -0.59
    POSITIVE LOGITS
     gifted
    1.14
     gifts
    0.87
    ocious
    0.83
     talents
    0.79
    Reviewer
    0.79
     athlet
    0.76
    inous
    0.75
    lings
    0.74
     gift
    0.73
    ening
    0.72
    Activations Density 0.009%

    No Known Activations