© 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. 17392
    Prev
    Next
    INDEX
    Explanations

    words related to physical features of the human face, particularly the nose

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "nose" and its variations in context

    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
    icity
    -0.78
     ILCS
    -0.76
    Population
    -0.75
     PowerPoint
    -0.74
    actionDate
    -0.71
    aneously
    -0.69
    atinum
    -0.69
    ERAL
    -0.68
     ACPI
    -0.67
    Leader
    -0.66
    POSITIVE LOGITS
    ble
    1.19
    cone
    1.19
     cone
    1.13
    bones
    1.09
    wash
    1.04
    beard
    1.02
     cones
    1.01
     hairs
    0.98
     wrink
    0.91
     cavity
    0.87
    Activations Density 0.019%

    No Known Activations