© 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. 2-RES-JB
    11. 23783
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement actions and legal procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with detention and encampment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.71
    itton
    -0.69
    GD
    -0.67
     breath
    -0.65
     crane
    -0.65
    REDACTED
    -0.64
     negatively
    -0.64
    ItemTracker
    -0.63
    NRS
    -0.62
    USE
    -0.61
    POSITIVE LOGITS
    ments
    2.22
    ment
    2.05
    MENTS
    1.54
    mented
    1.51
    mentation
    1.45
    mental
    1.39
    MENT
    1.36
    ties
    1.18
    ers
    1.09
    ership
    1.07
    Activations Density 0.049%

    No Known Activations