© 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. 11879
    Prev
    Next
    INDEX
    Explanations

    information related to status or characteristics of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is" followed by various attributes or roles of subjects

    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
    ridges
    -0.66
    urers
    -0.65
    ERG
    -0.64
    tenance
    -0.63
    ality
    -0.62
    ooters
    -0.61
    antics
    -0.61
    reating
    -0.60
    icators
    -0.60
    fail
    -0.59
    POSITIVE LOGITS
     redes
    0.74
    dinand
    0.74
     currently
    0.72
     incidentally
    0.71
     stationed
    0.71
     flanked
    0.70
     presided
    0.68
     presently
    0.68
     worshipped
    0.68
     briefed
    0.67
    Activations Density 0.136%

    No Known Activations