© 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. 11-RES-JB
    11. 15718
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating anticipation or warning of future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating predictions or expectations about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongh
    -0.70
     IPM
    -0.66
     prism
    -0.65
     resear
    -0.64
    tein
    -0.61
    rylic
    -0.60
     emphasizes
    -0.59
     emphasized
    -0.57
     quotas
    -0.57
     expertise
    -0.57
    POSITIVE LOGITS
     await
    1.28
     awaits
    1.20
     awaited
    1.14
     arise
    1.13
     happen
    1.12
    fall
    1.10
     ensued
    1.07
     unfold
    1.07
     Ahead
    1.06
     happens
    1.05
    Activations Density 0.360%

    No Known Activations