© 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. 4-RES-JB
    11. 20909
    Prev
    Next
    INDEX
    Explanations

    references to waterways or canals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various canals

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

    No Comments

    Negative Logits
    Reloaded
    -0.76
    ccording
    -0.75
    HCR
    -0.71
    ARS
    -0.70
    doms
    -0.69
    ARK
    -0.66
     Marketable
    -0.65
    ORN
    -0.65
    awn
    -0.65
    IRD
    -0.65
    POSITIVE LOGITS
     canal
    1.29
     Canal
    1.12
     reefs
    0.96
    ieri
    0.83
    akra
    0.75
    agin
    0.73
     tunnel
    0.72
    agall
    0.72
    obar
    0.72
     ditch
    0.69
    Activations Density 0.007%

    No Known Activations