© 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. 0-RES-JB
    6. 11855
    Prev
    Next
    INDEX
    Explanations

    the name "Amber" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Amber" and its variations, emphasizing the significance of this character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abba
    -0.78
    ranch
    -0.74
    apan
    -0.73
     pir
    -0.72
     Zamb
    -0.71
    DOC
    -0.70
     DOS
    -0.70
    å¯
    -0.69
     fram
    -0.67
     Pir
    -0.67
    POSITIVE LOGITS
     Amber
    3.56
    mber
    3.20
     amber
    1.87
     Ember
    1.61
    amber
    1.36
     Heather
    1.29
    nel
    1.21
     Jade
    1.17
     Violet
    1.14
     Brittany
    1.11
    Activations Density 0.036%

    No Known Activations