© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 702
    Prev
    Next
    INDEX
    Explanations

    words related to trains

    oai_token-act-pair · gpt-3.5-turbo

    the substring "ain", suggesting a focus on words that contain it

    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
     ZIP
    -0.68
     Javascript
    -0.64
     Glob
    -0.64
     zip
    -0.60
     eviction
    -0.60
     FIG
    -0.58
     vib
    -0.58
     revolving
    -0.57
     tet
    -0.57
     canceled
    -0.57
    POSITIVE LOGITS
    ain
    4.57
    ains
    2.55
    AIN
    2.20
    aine
    2.08
    ained
    2.01
    aining
    1.97
    ayn
    1.62
    aints
    1.59
    aint
    1.58
    ayne
    1.53
    Activations Density 0.010%

    No Known Activations