© 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. 10-RES-JB
    11. 1194
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or features

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to professional and technical applications

    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
    anon
    -0.72
    malink
    -0.68
     Revised
    -0.67
    ãĥĹ
    -0.66
    named
    -0.65
     affirmative
    -0.61
    ril
    -0.60
    toc
    -0.60
    FML
    -0.60
     Vote
    -0.60
    POSITIVE LOGITS
     applications
    1.14
     purposes
    1.10
     situations
    1.09
     contexts
    1.01
     environments
    0.96
     emergencies
    0.94
     workload
    0.90
     occasions
    0.88
     scenarios
    0.88
     alike
    0.87
    Activations Density 0.534%

    No Known Activations