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. 4-RES-JB
    6. 8735
    Prev
    Next
    INDEX
    Explanations

    references to famous fictional characters and figures

    oai_token-act-pair · gpt-3.5-turbo

    references to legendary or iconic characters from literature and film

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

    No Comments

    Negative Logits
    VL
    -0.75
    ITCH
    -0.72
    UB
    -0.71
     TAM
    -0.71
    AMY
    -0.68
    hold
    -0.68
    together
    -0.68
     RU
    -0.68
    æĢ
    -0.66
    onder
    -0.66
    POSITIVE LOGITS
     imperson
    0.96
     Mansion
    0.81
    hler
    0.76
     memor
    0.75
     spoof
    0.74
     imitation
    0.74
     parody
    0.73
     cartoons
    0.72
     movies
    0.72
     analogue
    0.72
    Activations Density 0.132%

    No Known Activations