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. 9-RES-JB
    6. 776
    Prev
    Next
    INDEX
    Explanations

    entities or organizations and their relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to ownership and control related to families and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Results
    -0.76
    ocket
    -0.73
    fulness
    -0.72
    fig
    -0.71
    brainer
    -0.71
    stories
    -0.71
    tackle
    -0.70
    phies
    -0.70
    notes
    -0.70
    epad
    -0.70
    POSITIVE LOGITS
     Confederacy
    1.09
     United
    1.07
     Communist
    1.04
     Clintons
    1.04
     bourgeoisie
    1.03
     Ministry
    1.01
     Republic
    1.00
     Soviets
    0.99
     likes
    0.97
     Knights
    0.96
    Activations Density 0.340%

    No Known Activations