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. 8536
    Prev
    Next
    INDEX
    Explanations

    references to specific periods of time, especially decades

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades and their associated cultural or historical events

    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
    Magikarp
    -0.66
     continu
    -0.64
     categ
    -0.60
     stret
    -0.60
    wat
    -0.58
     congr
    -0.58
    Fram
    -0.58
     Polic
    -0.56
     Cant
    -0.56
     propriet
    -0.55
    POSITIVE LOGITS
    ixties
    1.03
    -'
    0.87
    ties
    0.83
    inian
    0.82
    enium
    0.80
     onwards
    0.74
    yip
    0.74
    iatus
    0.70
    ounters
    0.70
    lins
    0.70
    Activations Density 0.064%

    No Known Activations