© 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. 7-RES-JB
    11. 23435
    Prev
    Next
    INDEX
    Explanations

    discussions or mentions of various news anchors and media personalities

    oai_token-act-pair · gpt-3.5-turbo

    references to media personalities and their programs

    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
    etsy
    -0.84
     unlocking
    -0.77
     unlocked
    -0.77
     sealing
    -0.73
    etooth
    -0.71
     erg
    -0.70
     unlock
    -0.69
     Saur
    -0.69
     concrete
    -0.69
    cles
    -0.69
    POSITIVE LOGITS
     broadcasts
    1.54
     airs
    1.39
     television
    1.38
     broadcast
    1.36
     TV
    1.31
     airing
    1.30
    levision
    1.25
     aired
    1.23
     podcasts
    1.22
     broadcaster
    1.21
    Activations Density 1.136%

    No Known Activations