© 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. 9-RES-JB
    11. 3488
    Prev
    Next
    INDEX
    Explanations

    instances where forgetting or being reminded of specific actions is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases that instruct or remind someone to remember to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.75
     inaction
    -0.74
     delusions
    -0.72
     impossibility
    -0.72
    ELD
    -0.71
    ãĤ¦ãĤ¹
    -0.69
    eur
    -0.68
    opoly
    -0.67
    democracy
    -0.67
     illusion
    -0.67
    POSITIVE LOGITS
     notify
    1.06
     check
    1.06
     mention
    1.03
     specify
    0.96
     ask
    0.93
     prioritize
    0.93
     delete
    0.91
     consult
    0.91
     warn
    0.90
     nominate
    0.89
    Activations Density 0.119%

    No Known Activations