© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 13487
    Prev
    Next
    INDEX
    Explanations

    words related to different types of poisons or poisoning incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of poison or poisoning incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noon
    -0.89
    pora
    -0.74
    dar
    -0.72
    ————
    -0.69
    tall
    -0.68
    aan
    -0.66
    peed
    -0.65
     Scouting
    -0.63
    sit
    -0.63
    mega
    -0.63
    POSITIVE LOGITS
     poisoning
    1.09
     poisoned
    0.97
     iv
    0.92
     poison
    0.91
     fumes
    0.91
     Ivy
    0.88
     arsenic
    0.88
     poisonous
    0.87
     gas
    0.86
     darts
    0.84
    Activations Density 0.026%

    No Known Activations