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. 4309
    Prev
    Next
    INDEX
    Explanations

    words related to ancient Greek history and mythology

    oai_token-act-pair · gpt-3.5-turbo

    references to ancient Greek history and figures

    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
    sheet
    -0.77
    blogs
    -0.75
    ierrez
    -0.72
    rador
    -0.71
    organ
    -0.70
    enegger
    -0.70
    AMI
    -0.70
     confidentiality
    -0.69
    ACTION
    -0.69
    raviolet
    -0.68
    POSITIVE LOGITS
     Romans
    0.99
     Augustus
    0.97
     Antiqu
    0.96
     ibn
    0.93
    ius
    0.93
     Aure
    0.91
    aeus
    0.89
    anus
    0.87
     Caesar
    0.87
     Herod
    0.86
    Activations Density 0.183%

    No Known Activations