© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15602
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the provision or offering of products, services, or information to various target audiences

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to various groups of individuals or target audiences

    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
    kun
    -0.75
    apo
    -0.71
    uncle
    -0.59
    obia
    -0.58
    staff
    -0.58
    Reuters
    -0.58
     Sheikh
    -0.58
    Capital
    -0.57
     Cipher
    -0.57
     juven
    -0.56
    POSITIVE LOGITS
     alike
    1.08
    hips
    0.83
    hip
    0.76
     everywhere
    0.73
     coping
    0.72
     who
    0.71
    place
    0.70
     acquainted
    0.70
     visualize
    0.68
    folk
    0.66
    Activations Density 0.180%

    No Known Activations