© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7041
    Prev
    Next
    INDEX
    Explanations

    words related to the color orange

    oai_token-act-pair · gpt-3.5-turbo

    instances of the color "orange" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Desc
    -0.84
    Ö¼
    -0.79
    sonian
    -0.77
    Requ
    -0.76
    fare
    -0.75
    Allow
    -0.72
    tle
    -0.72
    Engine
    -0.71
    follow
    -0.70
    iframe
    -0.70
    POSITIVE LOGITS
     orange
    1.32
     peel
    1.24
     oranges
    1.21
     juice
    1.11
     violet
    1.01
     coloured
    1.00
    orange
    0.99
     cones
    0.99
     Blossom
    0.97
     fruits
    0.97
    Activations Density 0.004%

    No Known Activations