© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 11945
    Prev
    Next
    INDEX
    Explanations

    words related to advancement or progression, especially in the context of technology and generations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to successive generations or groups in a context

    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
     sqor
    -0.92
    ļéĨĴ
    -0.84
     teasp
    -0.84
    uca
    -0.78
    iquette
    -0.75
    ilst
    -0.74
    hra
    -0.69
    parts
    -0.69
    ption
    -0.68
    Scotland
    -0.66
    POSITIVE LOGITS
     sorts
    0.79
     releases
    0.72
     endeavor
    0.68
     arrivals
    0.63
     RELE
    0.62
     entrants
    0.62
     diapers
    0.61
     iterations
    0.61
     unemploy
    0.61
     Axis
    0.60
    Activations Density 0.130%

    No Known Activations