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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 1156
    Prev
    Next
    INDEX
    Explanations

    sensations and emotions related to touch and physical experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal emotional sensations and feelings

    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
     Lies
    -0.68
     Tactics
    -0.66
     Secondly
    -0.64
     Agricultural
    -0.63
     Contest
    -0.62
     Spur
    -0.61
    licensed
    -0.61
     Trad
    -0.60
    esan
    -0.59
    adish
    -0.59
    POSITIVE LOGITS
     comfortable
    0.94
     vibrations
    0.93
     uneasy
    0.81
     sensations
    0.81
     compelled
    0.80
    ãĤ¶
    0.78
    rils
    0.74
     uncomfortable
    0.74
     sore
    0.73
     ashamed
    0.72
    Activations Density 0.036%

    No Known Activations