© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21407
    Prev
    Next
    INDEX
    Explanations

    the words "have a" followed by different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I have a" followed by various nouns and descriptors

    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
    advertising
    -0.81
    independence
    -0.78
    effects
    -0.78
    imar
    -0.75
    anthrop
    -0.73
    FIG
    -0.73
    Contents
    -0.71
    vale
    -0.70
    auri
    -0.70
    querade
    -0.69
    POSITIVE LOGITS
     problem
    1.17
     dilemma
    1.14
     feeling
    1.11
     question
    1.11
     backlog
    1.04
     sneaking
    1.03
     suggestion
    1.01
     clue
    1.00
     knack
    0.99
     choice
    0.98
    Activations Density 0.133%

    No Known Activations