© 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. 8-RES_POST_32K-OAI
    11. 8080
    Prev
    Next
    INDEX
    Explanations

    mentions of Wi-Fi and the Mi and Ki prefixes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    240
    +0.14
    0.6%
    558
    +0.10
    0.5%
    518
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.02
    57
    +0.10
    0.01
    326
    +0.09
    0.01
    Negative Logits
    姫
    -0.75
     Zucker
    -0.65
    nas
    -0.63
    LESS
    -0.63
    tics
    -0.62
     dispens
    -0.61
     Distribut
    -0.60
     Titus
    -0.60
     Devils
    -0.60
     Jarrett
    -0.59
    POSITIVE LOGITS
    pped
    1.03
    pping
    1.02
    pperc
    0.90
    omen
    0.89
    etooth
    0.89
    Fi
    0.88
    pless
    0.85
    isodes
    0.85
    Yo
    0.84
    veland
    0.83
    Activations Density 0.042%

    No Known Activations