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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 1622
    Prev
    Next
    INDEX
    Explanations

    instances where something is being forgotten or ignored

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "forget" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XY
    -0.70
    amen
    -0.69
    tained
    -0.69
    Parser
    -0.69
     nomine
    -0.68
     coefficients
    -0.68
    arte
    -0.68
    inals
    -0.67
    uana
    -0.67
    ullivan
    -0.65
    POSITIVE LOGITS
    fulness
    1.15
    fully
    0.99
    ful
    0.98
    theless
    0.91
     forgetting
    0.84
     forgot
    0.83
     forget
    0.83
    remember
    0.79
     remembered
    0.78
    ingly
    0.77
    Activations Density 0.020%

    No Known Activations