Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22924
    Prev
    Next
    INDEX
    Explanations

    phrases related to interpersonal interactions and physical actions

    oai_token-act-pair · gpt-3.5-turbo

    interactions filled with emotional weight and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osate
    -0.86
    displayText
    -0.79
     Berman
    -0.78
    busters
    -0.77
    SPONSORED
    -0.75
    Downloadha
    -0.74
    !'"
    -0.74
    govtrack
    -0.73
    Critics
    -0.71
    ,'"
    -0.70
    POSITIVE LOGITS
     Jaune
    1.04
     Weasley
    0.96
     Pyrrha
    0.93
     grin
    0.92
     shudder
    0.87
    blance
    0.85
     nodded
    0.84
     soothing
    0.84
     sighed
    0.83
     faint
    0.82
    Activations Density 0.670%

    No Known Activations