© 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. 6-RES-JB
    11. 3597
    Prev
    Next
    INDEX
    Explanations

    short prompts starting with the word "Remember"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "Remember," indicating a focus on nostalgia or recalling past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mehran
    -0.73
    elle
    -0.70
    goo
    -0.68
    Constructed
    -0.66
    hung
    -0.66
    irlf
    -0.65
    sels
    -0.63
    elled
    -0.63
    Beast
    -0.63
     Juda
    -0.63
    POSITIVE LOGITS
    remember
    0.92
     remembering
    0.82
     Recall
    0.74
     forgetting
    0.73
    ably
    0.72
     remember
    0.71
     forgotten
    0.70
     remembered
    0.70
     remembrance
    0.68
    theless
    0.67
    Activations Density 0.018%

    No Known Activations