© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 9969
    Prev
    Next
    INDEX
    Explanations

    terms related to media personalities and broadcasting

    oai_token-act-pair · gpt-3.5-turbo

    references to media formats and personalities associated with talk shows and punditry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsy
    -0.77
    urion
    -0.73
    jar
    -0.73
    aea
    -0.70
    potion
    -0.68
    Kind
    -0.67
    stan
    -0.64
    tnc
    -0.64
     Ballard
    -0.63
     Bagg
    -0.63
    POSITIVE LOGITS
     broadcasts
    1.35
     airs
    1.25
     commercials
    1.23
     broadcast
    1.18
     personalities
    1.17
     airing
    1.15
     broadcaster
    1.15
     stations
    1.14
     broadcasters
    1.13
     anchors
    1.13
    Activations Density 0.125%

    No Known Activations