© 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. 17325
    Prev
    Next
    INDEX
    Explanations

    comparative phrases comparing different levels or degrees of something

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that indicate an increase in quantity or quality

    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
    æ©
    -0.76
    lees
    -0.75
     Travels
    -0.74
     Contracts
    -0.73
     Loans
    -0.70
     Committees
    -0.69
     Provided
    -0.68
    marks
    -0.68
     Others
    -0.66
    pieces
    -0.66
    POSITIVE LOGITS
     efficient
    1.09
     complicated
    1.06
     nuanced
    1.02
     manageable
    1.01
     elaborate
    0.99
     sophisticated
    0.99
     plausible
    0.99
    than
    0.99
     than
    0.98
     expansive
    0.98
    Activations Density 0.040%

    No Known Activations