© 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. 15834
    Prev
    Next
    INDEX
    Explanations

    references to different types of rides or transportation methods, particularly with higher activations for amusement park rides

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of rides

    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
    organic
    -0.70
    Language
    -0.68
    556
    -0.68
     Primordial
    -0.68
    inity
    -0.67
    analy
    -0.66
     Analy
    -0.66
    utenberg
    -0.65
    Chelsea
    -0.64
    paragraph
    -0.64
    POSITIVE LOGITS
     rides
    3.63
     rode
    2.94
     ride
    2.73
     ridden
    2.02
     Ride
    1.94
     riding
    1.91
    ride
    1.71
     rider
    1.64
     riders
    1.61
     Riding
    1.51
    Activations Density 0.018%

    No Known Activations