© 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. 10-RES-JB
    11. 20332
    Prev
    Next
    INDEX
    Explanations

    terms related to subatomic particles and quantum physics

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to particle physics and quantum mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Homeless
    -0.79
     Grounds
    -0.76
     Bers
    -0.76
     Practices
    -0.75
     Peoples
    -0.75
    Weather
    -0.74
     Honduras
    -0.71
     menus
    -0.69
     Thailand
    -0.69
     Homes
    -0.68
    POSITIVE LOGITS
     particle
    1.29
     atoms
    1.24
     particles
    1.19
     ions
    1.14
     molecule
    1.12
     photons
    1.11
     Collider
    1.10
     photon
    1.08
     emitted
    1.06
     nucle
    1.05
    Activations Density 0.089%

    No Known Activations