© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4199
    Prev
    Next
    INDEX
    Explanations

    phrases related to scoring and achievements

    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
    763
    +0.12
    0.6%
    216
    +0.12
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.12
    0.03
    226
    +0.12
    0.03
    314
    +0.11
    -0.00
    Negative Logits
     vagina
    -0.70
     Sek
    -0.66
     disse
    -0.66
     ledger
    -0.63
     cartridge
    -0.61
     streetcar
    -0.61
     uterus
    -0.61
     roadmap
    -0.60
     Pastebin
    -0.60
    phrine
    -0.58
    POSITIVE LOGITS
    aret
    0.91
    Original
    0.89
    Hug
    0.79
    shr
    0.78
    Reviewer
    0.78
    ————————————————
    0.78
    alle
    0.77
    Bloom
    0.77
    ï¸ı
    0.75
    ————————
    0.75
    Activations Density 0.105%

    No Known Activations