© 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. 9444
    Prev
    Next
    INDEX
    Explanations

    words related to distance or progression away from a point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increasing distances or separations

    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
     LOT
    -0.62
    kes
    -0.61
    urated
    -0.60
     Swap
    -0.58
    TS
    -0.57
    RY
    -0.57
     ASP
    -0.56
    eson
    -0.56
    pport
    -0.55
     Stick
    -0.53
    POSITIVE LOGITS
     away
    1.30
     inland
    1.21
     apart
    1.15
     into
    1.10
    away
    1.08
     upstream
    1.04
     distances
    1.02
     downstream
    1.01
    forward
    1.00
     Away
    0.96
    Activations Density 0.060%

    No Known Activations