© 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. 6-RES-JB
    11. 2960
    Prev
    Next
    INDEX
    Explanations

    phrases related to the use of tools or instruments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that signify relationships or qualities, particularly those indicated by the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    notations
    -0.73
    bid
    -0.70
    etheus
    -0.69
    fur
    -0.68
    ptive
    -0.66
    xus
    -0.65
    gor
    -0.64
    cade
    -0.64
    idity
    -0.63
    bats
    -0.62
    POSITIVE LOGITS
     sorts
    1.32
     theirs
    0.91
     ours
    0.90
     hers
    0.85
    icial
    0.78
     civilisation
    0.74
    Measure
    0.72
    iversal
    0.70
     mine
    0.70
     pure
    0.69
    Activations Density 0.174%

    No Known Activations