© 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. 3-RES-JB
    6. 12182
    Prev
    Next
    INDEX
    Explanations

    words related to television ratings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ratings, specifically in relation to television shows and their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alz
    -0.73
    lessness
    -0.72
     Gibbs
    -0.71
    working
    -0.69
     Remem
    -0.69
     Paleo
    -0.66
    Dub
    -0.66
    uve
    -0.66
     Fathers
    -0.63
     Alm
    -0.62
    POSITIVE LOGITS
     ratings
    1.25
     rating
    1.07
     Ratings
    0.96
     Rating
    0.81
    omial
    0.79
     rated
    0.79
    awed
    0.79
     coefficients
    0.76
    Reviewer
    0.75
    otten
    0.75
    Activations Density 0.015%

    No Known Activations