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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 20233
    Prev
    Next
    INDEX
    Explanations

    references to the age of individuals, particularly minors in the context of negative actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to ages, particularly those associated with children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wikipedia
    -0.61
    hops
    -0.59
     lobb
    -0.59
     torches
    -0.59
    hesda
    -0.58
    Apps
    -0.57
    osponsors
    -0.57
    zsche
    -0.56
     VIDEOS
    -0.55
    ipedia
    -0.55
    POSITIVE LOGITS
     olds
    1.24
     old
    1.14
    old
    1.13
    olds
    0.94
     veteran
    0.90
    OLD
    0.90
    Old
    0.86
    -
    0.81
     Old
    0.80
     ago
    0.75
    Activations Density 0.027%

    No Known Activations