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. 16650
    Prev
    Next
    INDEX
    Explanations

    phrases related to readiness and anticipation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating readiness or awareness of upcoming events

    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
    terday
    -0.67
     awoken
    -0.65
    Christmas
    -0.64
    ranch
    -0.62
    oa
    -0.62
     originated
    -0.61
    pac
    -0.61
     originate
    -0.60
     stolen
    -0.60
     conspiring
    -0.59
    POSITIVE LOGITS
     yourselves
    1.04
     Yourself
    0.96
     yourself
    0.92
    !:
    0.75
     thou
    0.74
     Travels
    0.71
     References
    0.67
     CARE
    0.66
    uador
    0.65
    onnaissance
    0.65
    Activations Density 0.251%

    No Known Activations