© 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. 4-RES-JB
    11. 678
    Prev
    Next
    INDEX
    Explanations

    terms related to laws, legal cases, and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to civility and associated terms or figures in legal or cultural contexts

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

    No Comments

    Negative Logits
    hops
    -0.86
    ysis
    -0.81
    hop
    -0.74
    enment
    -0.70
    ocrine
    -0.66
    ocard
    -0.66
     mosqu
    -0.66
     glands
    -0.66
     Tend
    -0.66
    loader
    -0.65
    POSITIVE LOGITS
    adia
    0.92
    aii
    0.87
    asion
    0.86
    rans
    0.85
    asions
    0.83
    tg
    0.81
    dp
    0.80
    acity
    0.79
    ilt
    0.77
    aneers
    0.72
    Activations Density 0.026%

    No Known Activations