© 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. 10-RES-JB
    6. 16405
    Prev
    Next
    INDEX
    Explanations

    the phrase "declined to" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of someone declining to make a comment or provide details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.94
    selves
    -0.71
    ersed
    -0.66
     Indo
    -0.63
    abiding
    -0.63
     Compass
    -0.63
     Keeper
    -0.63
    asonic
    -0.59
     Veh
    -0.59
     Nurs
    -0.58
    POSITIVE LOGITS
     speculate
    1.44
     specify
    1.42
     comment
    1.40
     disclose
    1.38
     elaborate
    1.35
     characterize
    1.28
     discuss
    1.26
     clarify
    1.25
     divul
    1.23
     quantify
    1.15
    Activations Density 0.073%

    No Known Activations