© 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. 7-RES-JB
    11. 5264
    Prev
    Next
    INDEX
    Explanations

    proper nouns or entities mentioned within 'accounts'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey an assessment of situations or conditions based on various metrics

    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
    emen
    -0.77
     GOODMAN
    -0.75
    oday
    -0.73
     Citation
    -0.71
     Tags
    -0.68
     Enhancement
    -0.66
    rament
    -0.65
    ntil
    -0.65
    eties
    -0.63
     Tracks
    -0.63
    POSITIVE LOGITS
     resemble
    0.91
     excluded
    0.90
     absent
    0.87
     obliged
    0.79
     obliter
    0.77
     mistaken
    0.76
    forth
    0.76
     confined
    0.76
     compelled
    0.76
     distinguish
    0.75
    Activations Density 0.474%

    No Known Activations