© 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. 23168
    Prev
    Next
    INDEX
    Explanations

    words related to legal or criminal terms, particularly focusing on the term "rer" as part of words

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "erer," indicating a focus on specific roles or titles in a narrative

    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
     departments
    -0.70
    olulu
    -0.65
    acio
    -0.64
     clusters
    -0.63
    reek
    -0.62
    otted
    -0.61
     related
    -0.61
     unanimous
    -0.60
     Kund
    -0.60
    rise
    -0.59
    POSITIVE LOGITS
    erer
    1.34
    erers
    1.16
    xual
    0.96
    ufact
    0.88
    rer
    0.82
     beware
    0.78
    theless
    0.78
    ministic
    0.76
    iffe
    0.76
    cest
    0.73
    Activations Density 0.008%

    No Known Activations