© 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. 10-RES-JB
    11. 20521
    Prev
    Next
    INDEX
    Explanations

    data-related terms and sources

    oai_token-act-pair · gpt-3.5-turbo

    references to sources of information, particularly data and evidence from various platforms

    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
    Attempt
    -0.80
    inventoryQuantity
    -0.77
    nothing
    -0.76
    MpServer
    -0.76
    hor
    -0.74
    ãĥĻ
    -0.73
    ãĤ¨ãĥ«
    -0.73
    ãĥīãĥ©ãĤ´ãĥ³
    -0.71
    edi
    -0.71
    çĶ°
    -0.70
    POSITIVE LOGITS
     various
    1.12
     numerous
    1.06
     dozens
    1.02
     reputable
    0.95
     hundreds
    0.92
     several
    0.92
     Nielsen
    0.88
     multiple
    0.88
     stakeholders
    0.88
     thousands
    0.88
    Activations Density 0.412%

    No Known Activations