Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24453
    Prev
    Next
    INDEX
    Explanations

    phrases related to willingness or readiness to do something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "willing to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compass
    -0.86
    Offline
    -0.77
    ////////////////////////////////
    -0.74
    _.
    -0.73
    Facebook
    -0.72
    ARS
    -0.66
     Detected
    -0.66
    Veh
    -0.64
    Haunted
    -0.63
    Wan
    -0.63
    POSITIVE LOGITS
     accept
    1.14
     embrace
    1.14
     sacrifice
    1.03
     cooperate
    1.03
     give
    1.02
     abandon
    1.00
     tolerate
    0.98
     admit
    0.96
     undertake
    0.96
     sell
    0.95
    Activations Density 0.078%

    No Known Activations