© 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. 10-RES-JB
    11. 10768
    Prev
    Next
    INDEX
    Explanations

    instances where someone is reflecting or expressing regret over something they've said or done

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express hypothetical situations involving "have."

    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
    catentry
    -0.63
    center
    -0.60
     highlight
    -0.59
     Coffin
    -0.57
    COLOR
    -0.55
     Torrent
    -0.55
     smack
    -0.54
     reminder
    -0.53
    tip
    -0.53
    ishable
    -0.53
    POSITIVE LOGITS
     gotten
    1.21
     existed
    1.20
     survived
    1.19
     bothered
    1.14
     been
    1.13
    been
    1.09
     mattered
    1.07
     arisen
    1.07
     fared
    1.06
     intervened
    1.04
    Activations Density 0.085%

    No Known Activations