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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 5302
    Prev
    Next
    INDEX
    Explanations

    quantities related to large amounts or volumes

    oai_token-act-pair · gpt-3.5-turbo

    quantities of material or resources measured in tonnes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hall
    -0.70
     Assass
    -0.67
    gotten
    -0.67
     resemb
    -0.66
    comes
    -0.65
    leader
    -0.65
     Presidents
    -0.64
    govern
    -0.62
    States
    -0.61
    Leader
    -0.60
    POSITIVE LOGITS
     tonnes
    1.23
     lbs
    0.93
     litres
    0.90
    atsu
    0.87
     pounds
    0.86
     tons
    0.82
     kilograms
    0.81
     (£
    0.81
    ascus
    0.79
     stockpile
    0.78
    Activations Density 0.020%

    No Known Activations