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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 0-RES-JB
    6. 21095
    Prev
    Next
    INDEX
    Explanations

    phrases related to immediacy or urgency

    oai_token-act-pair · gpt-3.5-turbo

    references to urgent actions or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fest
    -0.75
    tery
    -0.71
     skew
    -0.64
    izen
    -0.63
    demon
    -0.60
    igr
    -0.60
    wash
    -0.59
    beard
    -0.59
     ske
    -0.59
    itcher
    -0.57
    POSITIVE LOGITS
     immediate
    3.72
    mediate
    1.76
     immedi
    1.70
     instantaneous
    1.66
     immediately
    1.61
     urgent
    1.49
     imminent
    1.47
     instant
    1.42
     Immediately
    1.33
     swift
    1.29
    Activations Density 0.005%

    No Known Activations