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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1802
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Sebastian."

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those associated with art and crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    robe
    -0.89
    marked
    -0.84
    rum
    -0.82
    acles
    -0.81
    sight
    -0.81
    ochond
    -0.80
    raq
    -0.78
    nings
    -0.77
    wich
    -0.77
    rug
    -0.77
    POSITIVE LOGITS
     Gomez
    0.96
     Garcia
    0.93
     Rossi
    0.93
     Rodriguez
    0.90
     Fernandez
    0.90
     Santos
    0.89
     Perez
    0.88
     Niño
    0.87
     Hernandez
    0.87
     Antonio
    0.86
    Activations Density 0.042%

    No Known Activations