© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29326
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions and references to instructional or supplemental materials

    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
    455
    +0.11
    0.5%
    402
    +0.11
    0.5%
    759
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.11
    0.07
    455
    +0.11
    0.08
    39
    +0.10
    0.07
    Negative Logits
    soType
    -0.85
    Merit
    -0.84
    psc
    -0.82
    doms
    -0.81
    Laughs
    -0.78
    gas
    -0.76
    cious
    -0.74
    eless
    -0.72
    Initialized
    -0.72
    ahu
    -0.71
    POSITIVE LOGITS
     links
    1.32
     instructions
    1.28
     diagrams
    1.26
     descriptions
    1.21
     screenshots
    1.21
     detailed
    1.21
     explanations
    1.15
     photographs
    1.14
     schematic
    1.14
     explanatory
    1.12
    Activations Density 1.107%

    No Known Activations