© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 440
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to reflecting on past events or making judgments based on past experience

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reflection and retrospective thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.76
    liam
    -0.72
    ayn
    -0.72
    yan
    -0.71
    bors
    -0.69
    hma
    -0.68
    vy
    -0.68
    risome
    -0.66
    mson
    -0.66
    eded
    -0.65
    POSITIVE LOGITS
     hindsight
    1.49
     retrospect
    1.35
    ibility
    0.89
     flashback
    0.81
     recollection
    0.81
    ãĥ¼ãĥĨ
    0.79
    itized
    0.77
     retrospective
    0.76
    DragonMagazine
    0.76
     guiActiveUn
    0.76
    Activations Density 0.008%

    No Known Activations