© 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. 2-RES-JB
    11. 1544
    Prev
    Next
    INDEX
    Explanations

    words related to the human nose and physical injury to the nose

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "nose."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.85
    20439
    -0.76
    aneously
    -0.72
    ERAL
    -0.71
    Avg
    -0.71
     ACPI
    -0.69
     PowerPoint
    -0.66
     Volunte
    -0.65
    inventoryQuantity
    -0.65
    RFC
    -0.64
    POSITIVE LOGITS
     nose
    1.12
     cone
    1.00
     noses
    0.99
     cones
    0.92
    ysis
    0.87
     Nose
    0.86
     pier
    0.86
    cone
    0.86
    bones
    0.86
     palate
    0.80
    Activations Density 0.005%

    No Known Activations