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. 6-RES-JB
    6. 2149
    Prev
    Next
    INDEX
    Explanations

    references to different forms of media and entertainment productions

    oai_token-act-pair · gpt-3.5-turbo

    elements and genres related to film and television production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.75
    wit
    -0.66
    finding
    -0.66
    oway
    -0.64
    hirt
    -0.64
     Maced
    -0.64
    placed
    -0.63
    eret
    -0.59
     embattled
    -0.59
    forth
    -0.58
    POSITIVE LOGITS
    rities
    0.87
    ocaust
    0.77
    netflix
    0.74
    ÃĥÃĤ
    0.73
    culosis
    0.73
     AUD
    0.72
    querque
    0.72
    ãĥŁ
    0.70
     Circus
    0.70
    apest
    0.69
    Activations Density 0.364%

    No Known Activations