© 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. 10-RES-JB
    11. 18545
    Prev
    Next
    INDEX
    Explanations

    mentions of potential scenarios with far-reaching effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to potential legal or political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.74
    orest
    -0.70
    @#&
    -0.66
     ALWAYS
    -0.65
    pection
    -0.64
    istent
    -0.64
     Detail
    -0.63
     fmt
    -0.62
    bey
    -0.59
    ateurs
    -0.59
    POSITIVE LOGITS
     someday
    1.27
     anytime
    0.93
     jeopardy
    0.91
     blackmail
    0.88
     potentially
    0.86
     sooner
    0.86
     future
    0.85
     retaliation
    0.83
     damaging
    0.83
     triggering
    0.82
    Activations Density 0.528%

    No Known Activations