© 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. 11-RES-JB
    11. 18563
    Prev
    Next
    INDEX
    Explanations

    significant numbers and quantities

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical values and related measurements in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NULL
    -0.75
    ebin
    -0.73
    ename
    -0.65
    Appearance
    -0.62
     srfAttach
    -0.62
    artifacts
    -0.59
     lieu
    -0.59
    wait
    -0.59
    ]=
    -0.59
     ç¥ŀ
    -0.58
    POSITIVE LOGITS
     seen
    1.11
     envisioned
    1.03
     touted
    0.98
     observed
    0.96
     contemplated
    0.95
     discussed
    0.95
     found
    0.94
     discovered
    0.93
     practiced
    0.93
     employed
    0.92
    Activations Density 0.455%

    No Known Activations