© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27420
    Prev
    Next
    INDEX
    Explanations

    terms related to nanotechnology and nanomaterials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.15
    0.7%
    730
    +0.12
    0.5%
    67
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.15
    0.00
    288
    +0.12
    0.02
    67
    +0.12
    0.02
    Negative Logits
     Typh
    -0.71
     Jarrett
    -0.65
     flared
    -0.62
     Gunn
    -0.62
     Scand
    -0.61
    BuyableInstoreAndOnline
    -0.61
     Scala
    -0.60
     Bengal
    -0.60
     Ange
    -0.59
     Fraz
    -0.58
    POSITIVE LOGITS
    otechnology
    1.33
    otech
    1.21
    ocry
    1.20
    owe
    1.12
    osc
    1.11
    jing
    1.04
    ocom
    1.02
    omach
    1.01
    ometer
    0.98
    obi
    0.95
    Activations Density 0.114%

    No Known Activations