© 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. 8-RES-JB
    11. 2761
    Prev
    Next
    INDEX
    Explanations

    phrases related to admiration or approval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appreciation and admiration for cinematic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •GPT2 Layer 8 Movie Sentiment Features

    No Comments

    Negative Logits
     Worse
    -0.81
    iatus
    -0.76
     indefinitely
    -0.75
    solete
    -0.74
    oubt
    -0.73
     Concern
    -0.73
     hereafter
    -0.73
     Alternatively
    -0.72
    Problem
    -0.71
    ivably
    -0.71
    POSITIVE LOGITS
     juxtap
    1.12
     versatility
    0.97
     Beaut
    0.94
     uniqueness
    0.92
     beautifully
    0.92
     gorgeous
    0.91
     simplicity
    0.91
     artic
    0.90
     accents
    0.89
     visuals
    0.88
    Activations Density 0.782%

    No Known Activations