© 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. 0-RES-JB
    11. 14832
    Prev
    Next
    INDEX
    Explanations

    the word "Chase"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Chase," indicating a focus on that specific entity

    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
     reg
    -0.73
     foc
    -0.67
    Î
    -0.67
    ublic
    -0.65
     unpopular
    -0.64
     abs
    -0.64
    const
    -0.63
    ources
    -0.63
     arg
    -0.62
     dist
    -0.61
    POSITIVE LOGITS
     Chase
    4.14
     Barcl
    1.27
     chase
    1.22
     JPMorgan
    1.19
     Sprint
    1.12
     Chevy
    1.02
     Wells
    1.02
     Dodge
    1.01
     Clayton
    0.99
     Chrysler
    0.97
    Activations Density 0.013%

    No Known Activations