© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2217
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions involving shaking one's head

    oai_token-act-pair · gpt-3.5-turbo

    references to physical gestures, particularly shaking a head or hands

    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
    DragonMagazine
    -0.79
    TABLE
    -0.70
    Secondly
    -0.70
    anza
    -0.68
    CLUS
    -0.66
     hereafter
    -0.65
    COMPLE
    -0.65
    Private
    -0.64
    EXP
    -0.64
    Buyable
    -0.63
    POSITIVE LOGITS
     toes
    1.01
     fingers
    0.99
     shoulders
    0.98
     eyel
    0.98
     toe
    0.94
     finger
    0.84
     tongue
    0.84
     neck
    0.80
     eyebrows
    0.80
     nose
    0.80
    Activations Density 0.175%

    No Known Activations