© 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. 8534
    Prev
    Next
    INDEX
    Explanations

    phrases indicating anticipation or expectation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "waiting to" indicating anticipation or expectation

    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
    quickShipAvailable
    -0.90
    goal
    -0.71
    holding
    -0.67
    grain
    -0.67
    ±
    -0.66
    sharp
    -0.66
    hered
    -0.65
    ¸
    -0.65
    problem
    -0.64
    ELF
    -0.63
    POSITIVE LOGITS
     hear
    1.05
     receive
    1.04
     capitalize
    1.03
     join
    1.02
     participate
    1.02
     enter
    1.01
     congratulate
    1.01
     get
    1.00
     reopen
    0.99
     speak
    0.99
    Activations Density 0.086%

    No Known Activations