© 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. 21513
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions or instances where something is being learned, typically involving the word "learnt"

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to learning and knowledge acquisition

    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
    ult
    -0.66
    odcast
    -0.66
    udge
    -0.64
    amen
    -0.64
    ankind
    -0.62
    senal
    -0.61
    oples
    -0.60
    orrow
    -0.60
    ouls
    -0.60
    larg
    -0.58
    POSITIVE LOGITS
     learnt
    1.24
    learn
    0.94
    Lear
    0.86
     learns
    0.84
     guesses
    0.84
    uren
    0.79
    æ©
    0.78
    tenance
    0.76
     unfocusedRange
    0.76
    CLASSIFIED
    0.76
    Activations Density 0.004%

    No Known Activations