© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3777
    Prev
    Next
    INDEX
    Explanations

    words related to poisons and toxicity

    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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noon
    -0.91
    pora
    -0.90
    dar
    -0.70
    aan
    -0.68
    ¬
    -0.68
    blance
    -0.67
    riots
    -0.64
    dimension
    -0.64
    RM
    -0.63
    sit
    -0.63
    POSITIVE LOGITS
     poisoning
    0.97
     iv
    0.94
     poison
    0.94
     dart
    0.92
     darts
    0.87
     gas
    0.87
    ously
    0.86
     Ivy
    0.86
     poisoned
    0.85
     pill
    0.81
    Activations Density 0.019%

    No Known Activations