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. 15696
    Prev
    Next
    INDEX
    Explanations

    references to a specific person with a name that includes "Ashraf" or "Varoufakis."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names and surnames

    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
     Roma
    -0.77
     Avalon
    -0.75
     Parenthood
    -0.69
    AX
    -0.66
     Genie
    -0.65
     Stamford
    -0.63
     Edison
    -0.61
     Giovanni
    -0.60
     Connor
    -0.60
     Pompe
    -0.60
    POSITIVE LOGITS
    shire
    0.92
    letcher
    0.88
    cffff
    0.86
    lisher
    0.82
    iture
    0.82
    idav
    0.82
    ugal
    0.80
    indal
    0.80
    cipled
    0.76
    entimes
    0.75
    Activations Density 0.036%

    No Known Activations