© 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. 6-RES-JB
    11. 17395
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical impact and collisions

    oai_token-act-pair · gpt-3.5-turbo

    the word "bump" and its variations, indicating a focus on impacts or collisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eval
    -0.77
     Ecology
    -0.72
    natureconservancy
    -0.72
    xious
    -0.68
    ANCE
    -0.68
     ministry
    -0.66
    ufact
    -0.65
    encia
    -0.64
    umerable
    -0.63
     FANT
    -0.62
    POSITIVE LOGITS
     bump
    0.95
     bumps
    0.92
    olean
    0.88
    sticks
    0.85
    balls
    0.83
    downs
    0.82
    stick
    0.81
    Ń·
    0.77
    alos
    0.76
    wagon
    0.76
    Activations Density 0.027%

    No Known Activations