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

    Neuronpedia

    Jacobian LensNEW
    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. 6645
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "forth" or phrases indicating back-and-forth movement or transitions

    oai_token-act-pair · gpt-3.5-turbo

    references to movement or progression

    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
    cius
    -0.70
    Quantity
    -0.65
     Priv
    -0.64
     Ventura
    -0.63
     Chile
    -0.62
     Beautiful
    -0.62
     Honduras
    -0.60
    ̶
    -0.60
     Guns
    -0.60
     Puerto
    -0.59
    POSITIVE LOGITS
    forth
    1.93
    comings
    1.07
    forward
    1.05
    coming
    0.97
    sburg
    0.96
    theless
    0.92
    soever
    0.89
    stairs
    0.85
    entimes
    0.85
    mares
    0.84
    Activations Density 0.007%

    No Known Activations