© 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. 2-RES-JB
    11. 17035
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "comprising"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate composition or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bell
    -0.65
     fly
    -0.60
    hound
    -0.59
     valve
    -0.58
     promoter
    -0.58
     Hound
    -0.58
     Vault
    -0.57
     lockout
    -0.57
     heel
    -0.57
     Bee
    -0.57
    POSITIVE LOGITS
    ngth
    1.02
     comprised
    1.01
     comprises
    0.99
     comprising
    0.99
    ogly
    0.81
    urally
    0.78
    umen
    0.76
     comprise
    0.76
    ussion
    0.76
    clusion
    0.75
    Activations Density 0.008%

    No Known Activations