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. 10835
    Prev
    Next
    INDEX
    Explanations

    references to a group of people, specifically, using the informal term "folks"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "folks."

    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
     Destination
    -0.63
    VL
    -0.62
    Course
    -0.60
    PM
    -0.60
    Weapon
    -0.60
     Supplement
    -0.59
    Charges
    -0.59
    ICO
    -0.58
    NN
    -0.58
     Cambodia
    -0.58
    POSITIVE LOGITS
    folk
    0.97
    hots
    0.95
    kies
    0.84
    ingen
    0.81
    hips
    0.78
    hao
    0.78
     who
    0.76
    tons
    0.76
    pace
    0.76
    hip
    0.75
    Activations Density 0.014%

    No Known Activations