© 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. 17632
    Prev
    Next
    INDEX
    Explanations

    keywords related to illegal activities such as electioneering, extortion, and money laundering

    oai_token-act-pair · gpt-3.5-turbo

    words related to structured roles or positions within a system

    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
     à¤
    -0.67
     Blessed
    -0.66
     DPR
    -0.63
    VL
    -0.62
     Sisters
    -0.61
    nant
    -0.61
     FAA
    -0.61
     cov
    -0.60
     Tid
    -0.58
     cowork
    -0.58
    POSITIVE LOGITS
    eer
    1.30
    eering
    1.22
    eers
    1.18
    minster
    0.85
    jriwal
    0.83
     herd
    0.82
    keye
    0.82
    wana
    0.81
    otin
    0.79
    aucuses
    0.78
    Activations Density 0.014%

    No Known Activations