© 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. 11-RES-JB
    11. 7783
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and coding tasks

    oai_token-act-pair · gpt-3.5-turbo

    instances where the word "we" is used, indicating a focus on collective action or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.62
     srfAttach
    -0.57
     Career
    -0.56
    azeera
    -0.56
     Failure
    -0.56
     Relief
    -0.55
     Warm
    -0.55
     pleading
    -0.55
     totality
    -0.55
     Excellence
    -0.54
    POSITIVE LOGITS
    're
    1.18
    'll
    1.18
     need
    1.00
     initialize
    0.98
    've
    0.97
     want
    0.97
     denote
    0.96
     assume
    0.90
    ighed
    0.90
     can
    0.88
    Activations Density 0.113%

    No Known Activations