© 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. 10-RES-JB
    11. 24039
    Prev
    Next
    INDEX
    Explanations

    phrases related to fatal events or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fatal incidents and death

    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
    yang
    -0.80
    erous
    -0.79
    yi
    -0.78
    here
    -0.76
    orthy
    -0.75
    wright
    -0.73
    orers
    -0.72
    arte
    -0.70
    hey
    -0.69
    erson
    -0.69
    POSITIVE LOGITS
     overdoses
    1.03
     flaw
    1.02
     overdose
    1.02
     gunshot
    1.02
     injection
    1.01
     shootings
    1.00
     blow
    0.99
     stabbing
    0.94
     dose
    0.94
     wounds
    0.93
    Activations Density 0.045%

    No Known Activations