© 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. 10633
    Prev
    Next
    INDEX
    Explanations

    terms related to respect

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of respect

    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
     Lans
    -1.00
    NetMessage
    -0.66
     concoct
    -0.64
     paran
    -0.64
     nerv
    -0.60
     advoc
    -0.58
     dreaming
    -0.58
     residue
    -0.57
     enthusi
    -0.57
     injunction
    -0.56
    POSITIVE LOGITS
    ability
    1.52
    ably
    1.29
    able
    1.12
    ible
    1.12
    fully
    1.05
    abilities
    1.05
    ibly
    1.05
    ility
    1.01
    amental
    0.97
    ibility
    0.94
    Activations Density 0.036%

    No Known Activations