© 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. 2-RES-JB
    11. 17222
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to rotation

    oai_token-act-pair · gpt-3.5-turbo

    words related to rotating or revolving actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.81
    esi
    -0.78
    hoff
    -0.77
    egu
    -0.74
    uk
    -0.72
    xx
    -0.72
    Dur
    -0.71
    ilk
    -0.69
    bour
    -0.69
    conom
    -0.69
    POSITIVE LOGITS
     rotating
    1.22
     rotated
    1.08
     rotate
    1.04
    entric
    0.81
     irregular
    0.76
     perspect
    0.76
    adoes
    0.75
     axis
    0.73
     swirl
    0.73
     Saunders
    0.73
    Activations Density 0.010%

    No Known Activations