© 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. 12640
    Prev
    Next
    INDEX
    Explanations

    mentions of tasks or activities that an organization or institution excels at

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that indicate complex relationships or comparisons

    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
     backup
    -0.56
    ipers
    -0.54
    berries
    -0.54
    $$$$
    -0.52
    gins
    -0.52
     Backup
    -0.52
    irens
    -0.52
    UP
    -0.51
    Blocks
    -0.51
    ttes
    -0.50
    POSITIVE LOGITS
     particularly
    0.80
     consequently
    0.73
     especially
    0.73
     indeed
    0.73
    particularly
    0.70
     insofar
    0.69
     vice
    0.68
     frankly
    0.68
     thence
    0.65
     necessarily
    0.64
    Activations Density 0.521%

    No Known Activations