© 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. 0-RES-JB
    11. 18899
    Prev
    Next
    INDEX
    Explanations

    words related to emotional restraint or lack of emotional expression, such as 'stoic' or 'spat'

    oai_token-act-pair · gpt-3.5-turbo

    words related to stoicism and emotional detachment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owered
    -0.76
     Bers
    -0.71
     Wilderness
    -0.71
    iris
    -0.70
     Expand
    -0.69
     Pants
    -0.68
    arthed
    -0.68
    urban
    -0.67
    photo
    -0.66
     Carnival
    -0.65
    POSITIVE LOGITS
     sto
    3.39
     spat
    1.68
     Sto
    1.38
     naive
    1.27
     naïve
    1.21
     Turing
    1.04
     altru
    1.04
     selfish
    1.03
     μ
    1.02
     finite
    0.96
    Activations Density 0.043%

    No Known Activations