© 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. 1-RES-JB
    11. 24292
    Prev
    Next
    INDEX
    Explanations

    words related to law

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "aw."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Panzer
    -0.77
     Juda
    -0.73
     Hitler
    -0.71
     Gemini
    -0.70
     Luthor
    -0.69
     shepherd
    -0.67
     Luther
    -0.67
     Schl
    -0.66
     Neptune
    -0.66
     Feld
    -0.65
    POSITIVE LOGITS
    aw
    1.49
    akening
    1.36
    akens
    1.27
    ashington
    1.20
    esome
    1.19
    aii
    1.15
    ards
    1.07
    aws
    1.07
    atche
    1.04
    keye
    1.00
    Activations Density 0.009%

    No Known Activations