© 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. 7342
    Prev
    Next
    INDEX
    Explanations

    Heavily focuses on detecting mentions of poisonous substances

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of poison

    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
    noon
    -0.83
    dar
    -0.72
    pora
    -0.67
    dimension
    -0.66
    blance
    -0.66
    irc
    -0.66
    Raid
    -0.64
    aan
    -0.64
    stand
    -0.63
     Scouting
    -0.63
    POSITIVE LOGITS
     poisoning
    1.11
     poison
    1.01
     poisoned
    0.97
     poisonous
    0.93
     dart
    0.93
     gas
    0.87
     arsenic
    0.84
    ously
    0.84
     darts
    0.83
     Ivy
    0.82
    Activations Density 0.012%

    No Known Activations