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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 23208
    Prev
    Next
    INDEX
    Explanations

    appearances of individuals in various media, such as films, TV shows, and productions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of appearances in various media and productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     learners
    -0.76
     administr
    -0.69
     ali
    -0.69
    ãĤ¦ãĤ¹
    -0.68
    soever
    -0.67
    .–
    -0.66
     disag
    -0.66
     disagrees
    -0.65
    hes
    -0.65
     knows
    -0.65
    POSITIVE LOGITS
     commercials
    1.01
     HBO
    1.00
     Celebrity
    0.96
     Playboy
    0.95
     ITV
    0.94
     films
    0.94
     Showtime
    0.93
     documentaries
    0.92
     Funny
    0.91
     Hulu
    0.90
    Activations Density 0.173%

    No Known Activations