© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 22845
    Prev
    Next
    INDEX
    Explanations

    phrases related to the nose

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "nose."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.84
     ILCS
    -0.82
    ERAL
    -0.76
     Volunte
    -0.72
     ACPI
    -0.71
    Avg
    -0.68
     PowerPoint
    -0.68
    HCR
    -0.67
     IGF
    -0.65
    aneously
    -0.64
    POSITIVE LOGITS
     cone
    1.05
     nose
    1.01
     cones
    1.00
    cone
    0.96
    bones
    0.93
     noses
    0.86
     pier
    0.86
    pipe
    0.85
    wash
    0.83
    bone
    0.82
    Activations Density 0.006%

    No Known Activations