© 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. 7-RES-JB
    11. 16744
    Prev
    Next
    INDEX
    Explanations

    positive expressions or compliments

    oai_token-act-pair · gpt-3.5-turbo

    positive adjectives and expressions of approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -1.01
    conservancy
    -0.89
    Downloadha
    -0.88
    obook
    -0.82
    velop
    -0.77
    à¨
    -0.76
    é¾į
    -0.76
    à©
    -0.75
    ãĥĺãĥ©
    -0.74
    ãģ®å®
    -0.73
    POSITIVE LOGITS
     huh
    0.92
     gotta
    0.87
     Thoughts
    0.82
     kidding
    0.82
    Sounds
    0.76
     classy
    0.76
     Advice
    0.74
     coincidence
    0.74
     irony
    0.73
    ly
    0.73
    Activations Density 0.225%

    No Known Activations