© 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. 1-RES-JB
    11. 13321
    Prev
    Next
    INDEX
    Explanations

    sensory experiences or physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sensations and sensory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olan
    -0.74
    dule
    -0.71
    otes
    -0.64
    alez
    -0.62
    aza
    -0.61
    min
    -0.61
    erity
    -0.61
    err
    -0.61
    arching
    -0.61
    annis
    -0.59
    POSITIVE LOGITS
     sensation
    1.36
     sensations
    1.34
    terness
    1.08
     gratification
    0.85
    waves
    0.81
    geoning
    0.80
    çIJ
    0.80
    ually
    0.79
     darling
    0.77
    ual
    0.76
    Activations Density 0.005%

    No Known Activations