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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 808
    Prev
    Next
    INDEX
    Explanations

    language related to different professions, such as journalist, writer, producer, director, and actor

    oai_token-act-pair · gpt-3.5-turbo

    elements related to journalism and film production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.73
     wired
    -0.66
    stan
    -0.65
    rontal
    -0.65
     annexed
    -0.64
     centrif
    -0.63
     airspace
    -0.63
     highways
    -0.63
     unpop
    -0.63
    ppings
    -0.62
    POSITIVE LOGITS
    iquette
    0.74
    enment
    0.72
    Publisher
    0.71
    ateur
    0.69
    olkien
    0.68
     Leigh
    0.67
     Nou
    0.66
    editor
    0.65
    angelo
    0.64
    sonian
    0.63
    Activations Density 0.682%

    No Known Activations