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. 2-RES-JB
    6. 9825
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly the name "Alberto"

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those of individuals, in the text

    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
    sylv
    -0.76
    wich
    -0.74
    awar
    -0.73
    elling
    -0.72
    rug
    -0.71
    benefit
    -0.71
    ymph
    -0.70
    DIV
    -0.70
    tnc
    -0.68
    otin
    -0.68
    POSITIVE LOGITS
     Enrique
    1.14
     Julio
    1.08
     Fernandez
    1.08
     Paulo
    1.07
     Niño
    1.06
     Alberto
    1.04
     Lorenzo
    1.03
     Gonz
    1.02
     Ricardo
    1.02
     Santiago
    1.00
    Activations Density 0.018%

    No Known Activations