© 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. 3-RES-JB
    11. 13161
    Prev
    Next
    INDEX
    Explanations

    references to multiple generations or the passing of time down familial lines

    oai_token-act-pair · gpt-3.5-turbo

    references to "generations" and discussions about their influence or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.89
    pmwiki
    -0.74
    acl
    -0.69
    ournals
    -0.66
    ibrary
    -0.64
    yer
    -0.63
    olulu
    -0.62
    aleigh
    -0.61
    ope
    -0.61
     systematic
    -0.60
    POSITIVE LOGITS
     generations
    1.05
     Generations
    1.03
     ago
    0.79
     msec
    0.76
    arily
    0.74
     bred
    0.72
     ages
    0.72
     grandchildren
    0.70
     elders
    0.67
     Lear
    0.67
    Activations Density 0.011%

    No Known Activations