© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16701
    Prev
    Next
    INDEX
    Explanations

    features and attributes related to the design and physical characteristics of products

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to product design and ergonomics

    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
    aunder
    -0.83
    mire
    -0.82
    respect
    -0.81
    unicip
    -0.80
    gdala
    -0.79
    uphem
    -0.79
    onis
    -0.77
    #$#$
    -0.77
    OPA
    -0.76
    mr
    -0.75
    POSITIVE LOGITS
     design
    1.30
     exterior
    1.19
     styling
    1.17
     shape
    1.13
     appearance
    1.12
     silhouette
    1.12
     chassis
    1.09
     layout
    1.09
     designs
    1.08
     interior
    1.06
    Activations Density 0.201%

    No Known Activations