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. 2141
    Prev
    Next
    INDEX
    Explanations

    words related to organization and coordination efforts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "organizing."

    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
    ixed
    -0.79
    ilings
    -0.71
    rendered
    -0.71
    den
    -0.70
    gam
    -0.69
    worth
    -0.69
    othy
    -0.68
    bole
    -0.67
    plays
    -0.66
    Den
    -0.64
    POSITIVE LOGITS
    eering
    1.03
    izational
    0.98
    eers
    0.90
     organizing
    0.86
     organising
    0.84
    arity
    0.78
     organizer
    0.77
     committees
    0.77
     committee
    0.76
     caucuses
    0.76
    Activations Density 0.025%

    No Known Activations