© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9626
    Prev
    Next
    INDEX
    Explanations

    adjectives describing intensity or completeness

    oai_token-act-pair · gpt-3.5-turbo

    words associated with completeness or fullness

    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
    apego
    -0.77
    encer
    -0.72
    apter
    -0.71
    ndra
    -0.70
    tis
    -0.70
     Flavoring
    -0.69
    vous
    -0.68
     Founders
    -0.67
    ourge
    -0.67
    ramid
    -0.67
    POSITIVE LOGITS
     increments
    1.06
     guise
    0.95
     fashion
    0.94
     manner
    0.91
     circles
    0.90
     proportions
    0.89
     stead
    0.88
     quantities
    0.87
     terms
    0.86
     arenas
    0.86
    Activations Density 0.177%

    No Known Activations