© 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. 10-RES-JB
    11. 11474
    Prev
    Next
    INDEX
    Explanations

    the letter "g" followed by verbs or adjectives

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'g' in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tenance
    -0.72
     Ideal
    -0.70
     Exile
    -0.69
    etheless
    -0.67
     questioning
    -0.61
    Ô
    -0.60
     reproduction
    -0.60
     Lack
    -0.59
     compet
    -0.59
     Inspection
    -0.58
    POSITIVE LOGITS
    ourmet
    1.40
    rafted
    1.31
    ilded
    1.27
    auntlet
    1.26
    ospels
    1.22
    remlin
    1.21
    oliath
    1.21
    auntlets
    1.18
    ulp
    1.17
    endered
    1.17
    Activations Density 0.027%

    No Known Activations