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. 3-RES-JB
    6. 954
    Prev
    Next
    INDEX
    Explanations

    mentions of a decrease in rank or position

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dem" or related variations, indicating a focus on themes related to democracy or democratic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAYS
    -0.87
    Pull
    -0.71
    akeru
    -0.70
    hetti
    -0.70
    gerald
    -0.69
    tis
    -0.69
    URN
    -0.67
    ORY
    -0.67
    OWS
    -0.67
    ा
    -0.65
    POSITIVE LOGITS
    agogue
    1.11
    agog
    1.07
    ilit
    0.95
     dem
    0.94
    ographically
    0.94
    ploy
    0.92
    onym
    0.88
    igration
    0.87
    otions
    0.87
    onse
    0.86
    Activations Density 0.005%

    No Known Activations