© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2179
    Prev
    Next
    INDEX
    Explanations

    names of entertainment and media companies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of film and television studios or networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adin
    -0.73
    jriwal
    -0.71
     subsistence
    -0.71
    obyl
    -0.67
    phy
    -0.66
    anooga
    -0.64
    milo
    -0.64
    jri
    -0.64
     sshd
    -0.64
    _>
    -0.63
    POSITIVE LOGITS
     Studios
    1.34
     Films
    1.21
     Television
    1.15
     Entertainment
    1.06
     Presents
    0.97
    ovies
    0.97
     Premiere
    0.97
     Movies
    0.96
    TV
    0.96
     Productions
    0.95
    Activations Density 0.169%

    No Known Activations