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. 23721
    Prev
    Next
    INDEX
    Explanations

    keywords related to popular TV shows and video games

    oai_token-act-pair · gpt-3.5-turbo

    titles and series names associated with popular media

    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
    housing
    -0.70
    efe
    -0.70
    private
    -0.67
    ¿½
    -0.66
     VIEW
    -0.65
    prus
    -0.65
    ESSION
    -0.64
    ession
    -0.64
    aye
    -0.64
    mand
    -0.64
    POSITIVE LOGITS
     sequels
    0.97
     trilogy
    0.84
     fandom
    0.81
     films
    0.81
     sequel
    0.80
     Characters
    0.79
     Animated
    0.78
     arcs
    0.77
     franchises
    0.77
     trope
    0.76
    Activations Density 0.041%

    No Known Activations