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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 23361
    Prev
    Next
    INDEX
    Explanations

    words related to press secretaries

    oai_token-act-pair · gpt-3.5-turbo

    references to press secretaries and related roles in the context of government communications

    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
    abbage
    -0.78
    interest
    -0.77
    paying
    -0.72
    vasive
    -0.72
    liga
    -0.71
    esm
    -0.69
    urious
    -0.68
     [|
    -0.67
    UCT
    -0.65
    avascript
    -0.65
    POSITIVE LOGITS
     Ari
    0.82
     Betsy
    0.75
    Anne
    0.73
     Sean
    0.72
     Katie
    0.72
     aide
    0.71
     Suzanne
    0.70
     CTR
    0.68
     Ernst
    0.68
     Emails
    0.67
    Activations Density 0.079%

    No Known Activations