© 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. 2-RES-JB
    11. 361
    Prev
    Next
    INDEX
    Explanations

    keywords related to locations in a directional sense, such as upstream and downstream

    oai_token-act-pair · gpt-3.5-turbo

    directional references related to water flow (specifically "upstream" and "downstream")

    oai_token-act-pair · gpt-4-turbo

    terms related to directional flow in processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasis
    -0.79
    itia
    -0.77
     Manson
    -0.75
    ces
    -0.73
    pmwiki
    -0.67
     Patton
    -0.66
    inea
    -0.66
    berman
    -0.65
    orian
    -0.64
    nam
    -0.64
    POSITIVE LOGITS
     downstream
    1.35
     upstream
    1.25
    stream
    0.78
    edIn
    0.72
     propagation
    0.71
    side
    0.71
     watershed
    0.71
    externalActionCode
    0.70
     prelim
    0.70
    layer
    0.69
    Activations Density 0.006%

    No Known Activations