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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 812
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical actions and sensations

    oai_token-act-pair · gpt-3.5-turbo

    phrases depicting physical sensations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Founders
    -0.78
     Founding
    -0.78
     Historically
    -0.74
     Inher
    -0.73
     Policies
    -0.67
     Settlement
    -0.66
    chnology
    -0.65
     Nationwide
    -0.65
     tariffs
    -0.64
     Markets
    -0.64
    POSITIVE LOGITS
     faint
    0.87
     throb
    0.84
     audible
    0.84
     numb
    0.83
     startled
    0.82
     crou
    0.81
     vibr
    0.80
     erection
    0.80
     gasp
    0.79
     curled
    0.79
    Activations Density 1.111%

    No Known Activations