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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4508
    Prev
    Next
    INDEX
    Explanations

    references to particle physics and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to particle physics and related terminology

    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
    chin
    -0.75
    ients
    -0.71
    robat
    -0.71
    --------------------------------------------------------
    -0.70
    ript
    -0.67
    lua
    -0.65
    vag
    -0.65
     Kush
    -0.64
    othy
    -0.64
     Og
    -0.64
    POSITIVE LOGITS
    ERN
    1.29
     Collider
    1.08
     physicist
    1.07
     physicists
    0.95
     particle
    0.90
     accelerator
    0.86
    IFIED
    0.84
     neutron
    0.78
    DATA
    0.76
    arium
    0.76
    Activations Density 0.011%

    No Known Activations