© 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. 0-RES-JB
    11. 10345
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that are remembered for certain characteristics or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to memories and the concept of remembering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     premise
    -0.63
     defect
    -0.62
     licence
    -0.61
     license
    -0.61
    Demand
    -0.61
     mandate
    -0.60
    brid
    -0.59
     request
    -0.58
     applications
    -0.57
     spectrum
    -0.57
    POSITIVE LOGITS
     remembered
    3.89
     remembers
    2.26
     recalled
    2.08
     remembering
    1.86
     remember
    1.75
     remem
    1.70
    remember
    1.49
     recol
    1.45
     forgotten
    1.44
     recollection
    1.35
    Activations Density 0.010%

    No Known Activations