© 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. 11-RES-JB
    11. 22517
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "have" followed by some additional description or context

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "we have" in various contexts

    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
    cone
    -0.75
    eem
    -0.74
    oshi
    -0.70
    drive
    -0.68
    tip
    -0.68
    conom
    -0.67
    roll
    -0.65
    alter
    -0.65
    ensing
    -0.63
    icking
    -0.62
    POSITIVE LOGITS
     seen
    1.20
     ourselves
    1.14
     witnessed
    1.07
     heard
    1.05
     been
    0.96
     talked
    0.96
     learned
    0.95
     gotten
    0.95
     reached
    0.94
     learnt
    0.92
    Activations Density 0.134%

    No Known Activations