© 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. 0-RES-JB
    11. 12013
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant or extreme changes or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant changes or remarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ACS
    -0.72
     Corpus
    -0.71
     linked
    -0.71
    anon
    -0.70
    aza
    -0.68
     sclerosis
    -0.67
     Heights
    -0.66
    otto
    -0.64
     Neuroscience
    -0.63
     winners
    -0.63
    POSITIVE LOGITS
     drastic
    1.77
     remark
    1.35
     deem
    1.11
     scarce
    1.08
     drastically
    1.04
    frey
    1.03
     glaring
    1.02
     concerted
    0.95
     recourse
    0.94
     foresee
    0.94
    Activations Density 0.069%

    No Known Activations