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. 4541
    Prev
    Next
    INDEX
    Explanations

    phrases related to memories or thoughts coming to mind

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss thoughts or recollections, particularly those beginning with "comes to mind" or similar expressions

    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
     MSG
    -0.70
    ongyang
    -0.69
     Caps
    -0.68
    achus
    -0.63
    aldi
    -0.62
    uphem
    -0.62
    IQ
    -0.62
    nic
    -0.61
    erva
    -0.59
    alted
    -0.59
    POSITIVE LOGITS
    ãĤ¼
    0.75
    ç«
    0.73
    å§«
    0.68
    éĹ
    0.66
    lihood
    0.66
    ONT
    0.65
    к
    0.62
    æ©
    0.61
    steps
    0.60
    _-_
    0.60
    Activations Density 0.041%

    No Known Activations