© 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. 11-RES-JB
    11. 9926
    Prev
    Next
    INDEX
    Explanations

    mentions of people's deaths, including locations and ages

    oai_token-act-pair · gpt-3.5-turbo

    references to death and associated details such as time and place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.81
    ãĥ¼ãĤ¯
    -0.76
    soDeliveryDate
    -0.72
    selves
    -0.71
    notation
    -0.70
    jab
    -0.68
    XY
    -0.68
    bies
    -0.68
    Girls
    -0.67
    gey
    -0.67
    POSITIVE LOGITS
     childbirth
    1.21
     hosp
    1.00
     hospital
    0.98
     infancy
    0.93
     cardiac
    0.86
     crem
    0.85
     prison
    0.82
     renal
    0.81
     liver
    0.81
     tragically
    0.79
    Activations Density 0.097%

    No Known Activations