© 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. 10-RES-JB
    6. 1150
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviewing products

    oai_token-act-pair · gpt-3.5-turbo

    evaluative terms related to product quality and features

    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
    Social
    -0.73
     Yiannopoulos
    -0.72
     yawn
    -0.70
    ongo
    -0.70
    Population
    -0.69
     tweets
    -0.67
    social
    -0.65
    iberal
    -0.65
    football
    -0.64
    ognitive
    -0.64
    POSITIVE LOGITS
     Manufacturer
    1.52
     manufacturer
    1.51
     OEM
    1.43
     manufacturers
    1.40
     warranty
    1.40
     manufacture
    1.37
     manufactures
    1.36
     manufact
    1.29
     accessories
    1.26
    Manufact
    1.26
    Activations Density 1.093%

    No Known Activations