© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 7667
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific imaging techniques

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to imaging and scientific measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rebell
    -0.86
    lord
    -0.75
     Revival
    -0.75
     Rebellion
    -0.75
    cakes
    -0.73
    joy
    -0.72
    ifest
    -0.71
     Ending
    -0.70
     kisses
    -0.70
    âĶģ
    -0.70
    POSITIVE LOGITS
     detecting
    1.33
     scanning
    1.32
     predictive
    1.29
     analytical
    1.28
     detect
    1.28
     monitoring
    1.27
     surve
    1.27
    analy
    1.25
     databases
    1.24
     analys
    1.24
    Activations Density 1.139%

    No Known Activations