Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 12301
    Prev
    Next
    INDEX
    Explanations

    words related to political actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to political or social issues and their implications

    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
    $.
    -0.71
    âĹ¼
    -0.70
    urnal
    -0.69
    é¾įå
    -0.69
    EStreamFrame
    -0.68
    Foreign
    -0.65
    fml
    -0.65
    rather
    -0.65
    foreign
    -0.65
    stellar
    -0.64
    POSITIVE LOGITS
     consists
    1.04
    ariat
    0.97
     comprises
    0.92
     consisted
    0.88
     dilemma
    0.76
     motto
    0.75
     has
    0.74
     contains
    0.73
     is
    0.73
     provides
    0.71
    Activations Density 0.552%

    No Known Activations