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. 14581
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or campaigns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of organizations, notable individuals, and institutions related to social issues and legal contexts

    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
    frame
    -0.90
    fram
    -0.84
    rome
    -0.84
    station
    -0.82
    wagen
    -0.80
    stay
    -0.80
    frames
    -0.79
    hab
    -0.79
    uten
    -0.78
    train
    -0.77
    POSITIVE LOGITS
     NAACP
    1.00
     GOODMAN
    0.84
    ONSORED
    0.82
     Cosponsors
    0.78
     glim
    0.78
    ICS
    0.77
    ENTS
    0.76
     Legal
    0.74
    ACP
    0.73
    resents
    0.73
    Activations Density 0.026%

    No Known Activations