© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11980
    Prev
    Next
    INDEX
    Explanations

    phrases related to transportation or lifting objects/people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lift" in various contexts and meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gon
    -0.71
    ulhu
    -0.67
     Tec
    -0.67
     Tul
    -0.67
    haps
    -0.66
     Devices
    -0.66
    script
    -0.66
     Ide
    -0.66
    offic
    -0.65
     Deb
    -0.65
    POSITIVE LOGITS
     lift
    3.81
     lifts
    2.73
    lift
    2.70
     Lift
    2.56
     lifting
    2.50
     lifted
    2.04
    lifting
    1.64
     climb
    1.27
     snatch
    1.27
     ride
    1.26
    Activations Density 0.020%

    No Known Activations