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. 3789
    Prev
    Next
    INDEX
    Explanations

    mentions of people in social contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of people

    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
     srfAttach
    -0.81
    NES
    -0.79
    SPONSORED
    -0.72
    SET
    -0.70
    ener
    -0.67
     Lank
    -0.67
    Emer
    -0.67
    Material
    -0.67
    Accessory
    -0.66
    uner
    -0.65
    POSITIVE LOGITS
     smugglers
    1.00
    folk
    0.86
     who
    0.77
    etheless
    0.68
     starve
    0.68
    wana
    0.67
     everywhere
    0.66
    hate
    0.66
     died
    0.64
     traffickers
    0.64
    Activations Density 0.088%

    No Known Activations