© 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. 5776
    Prev
    Next
    INDEX
    Explanations

    mentions of lethal actions or items

    oai_token-act-pair · gpt-3.5-turbo

    references to lethal concepts or events

    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
    angles
    -0.79
    rix
    -0.77
    ebook
    -0.77
    roo
    -0.77
    romy
    -0.76
    arest
    -0.74
    Rate
    -0.74
    acular
    -0.73
    ramid
    -0.72
    arte
    -0.71
    POSITIVE LOGITS
     lethal
    1.08
     injection
    1.03
    etheless
    0.97
    otine
    0.91
    lethal
    0.86
     assassins
    0.85
     mosqu
    0.85
     assassin
    0.84
     injections
    0.83
    espie
    0.82
    Activations Density 0.010%

    No Known Activations