© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22667
    Prev
    Next
    INDEX
    Explanations

    adjectives related to subdued or restrained emotions or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to muted or subdued qualities and emotions

    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
    initions
    -0.74
    htt
    -0.72
     Eagle
    -0.72
     SI
    -0.68
    agra
    -0.68
     superst
    -0.66
    Gate
    -0.65
     PI
    -0.65
     Biological
    -0.65
    RF
    -0.65
    POSITIVE LOGITS
     muted
    3.33
     subdued
    2.29
     restrained
    1.59
     mute
    1.48
     vibrant
    1.38
     tame
    1.28
     sep
    1.27
     vivid
    1.11
     saturated
    1.09
     faded
    1.09
    Activations Density 0.054%

    No Known Activations