© 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. 8-RES-JB
    11. 4280
    Prev
    Next
    INDEX
    Explanations

    phrases related to reflecting on past events or hindsight

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reflection and the evaluation of past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unin
    -0.61
    aves
    -0.60
     minorities
    -0.59
    ĺħ
    -0.59
    CONT
    -0.58
    liam
    -0.58
    bors
    -0.57
    anto
    -0.56
    ya
    -0.56
    vic
    -0.56
    POSITIVE LOGITS
     hindsight
    1.15
     retrospect
    1.01
    spection
    0.92
    ibility
    0.90
     nostalg
    0.86
     recollection
    0.79
    raft
    0.78
    spective
    0.76
    herty
    0.74
    ively
    0.73
    Activations Density 0.058%

    No Known Activations