© 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. 17348
    Prev
    Next
    INDEX
    Explanations

    terms related to youth programs or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to youth and youth-related topics

    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
    pard
    -0.79
    ãĤ´ãĥ³
    -0.74
    eus
    -0.71
    essen
    -0.70
    ++++++++
    -0.70
    ++++++++++++++++
    -0.69
    ichick
    -0.69
    asel
    -0.69
    rosis
    -0.68
    iment
    -0.66
    POSITIVE LOGITS
    fulness
    1.12
    uates
    0.85
    ful
    0.85
    doms
    0.83
     unemployment
    0.82
     delinqu
    0.81
    sters
    0.81
     ages
    0.80
    fully
    0.79
     outreach
    0.78
    Activations Density 0.025%

    No Known Activations