Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 110
    Prev
    Next
    INDEX
    Explanations

    individuals working in the entertainment industry as writers, directors, producers, and artists

    oai_token-act-pair · gpt-3.5-turbo

    references to various creative professionals and their collaborations in film and music

    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
    yip
    -1.02
    ibaba
    -0.80
    Ĥİ
    -0.74
    bia
    -0.71
    ulin
    -0.67
    idium
    -0.66
    ecause
    -0.66
    ramid
    -0.65
    anqu
    -0.65
     outbreaks
    -0.64
    POSITIVE LOGITS
     artist
    1.03
    artist
    1.02
     artists
    1.01
    Publisher
    0.96
    Artist
    0.96
     designer
    0.94
     screenplay
    0.94
    director
    0.92
     musician
    0.90
     studio
    0.90
    Activations Density 0.398%

    No Known Activations