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. 7-RES-JB
    6. 17010
    Prev
    Next
    INDEX
    Explanations

    the word "past" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to past events or prior occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    claimer
    -0.81
    hyde
    -0.80
    ucker
    -0.76
    ifle
    -0.75
     Pledge
    -0.74
    iece
    -0.74
    ocracy
    -0.74
    phe
    -0.74
    ikh
    -0.73
    iphate
    -0.71
    POSITIVE LOGITS
     generations
    1.47
     iterations
    1.11
     developments
    1.09
     versions
    1.06
     trends
    0.99
     predecessors
    0.98
     editions
    0.98
     incarn
    0.95
     eras
    0.95
     episodes
    0.93
    Activations Density 0.143%

    No Known Activations