© 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. 32191
    Prev
    Next
    INDEX
    Explanations

    terms related to innovative materials and their applications in technology

    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
    439
    +0.12
    0.5%
    516
    +0.10
    0.5%
    656
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.16
    594
    +0.10
    0.11
    575
    +0.10
    0.13
    Negative Logits
    zzy
    -0.79
    adelphia
    -0.75
     Maced
    -0.73
     Dunk
    -0.73
     Pew
    -0.72
     Username
    -0.71
    76561
    -0.71
     haun
    -0.70
     muted
    -0.69
     unpaid
    -0.68
    POSITIVE LOGITS
     architectures
    1.42
     technologies
    1.36
     technology
    1.33
     nanop
    1.22
     nan
    1.20
    technology
    1.19
     fabrication
    1.19
     propulsion
    1.17
     architecture
    1.14
     electronics
    1.13
    Activations Density 1.940%

    No Known Activations