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. 3148
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or groups with the word "Council" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to various councils and their activities

    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
    Downloadha
    -0.77
     experien
    -0.72
    icio
    -0.69
    ionage
    -0.64
    dates
    -0.64
    udeau
    -0.64
    aneous
    -0.61
    CRIP
    -0.61
     endings
    -0.58
     Meier
    -0.58
    POSITIVE LOGITS
    members
    0.97
    member
    0.97
     Council
    0.89
     Chambers
    0.81
    ors
    0.78
    redits
    0.76
     Members
    0.75
    walk
    0.74
    shed
    0.74
    pers
    0.74
    Activations Density 0.017%

    No Known Activations