Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3512
    Prev
    Next
    INDEX
    Explanations

    the word "forget" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "forget," "forgot," and their variations

    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
    amen
    -0.67
    berus
    -0.66
     coefficients
    -0.66
    orough
    -0.65
    Ec
    -0.65
    inals
    -0.64
    XY
    -0.64
    elled
    -0.62
    é¾
    -0.62
    tained
    -0.61
    POSITIVE LOGITS
    fulness
    1.16
    fully
    1.06
    ful
    1.03
    ingly
    0.78
    lore
    0.78
     forgetting
    0.77
     forgot
    0.77
    noon
    0.77
    ening
    0.75
    remember
    0.74
    Activations Density 0.022%

    No Known Activations