© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 6007
    Prev
    Next
    INDEX
    Explanations

    occurrences of sample sizes in statistical 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
    373
    +0.21
    0.9%
    596
    +0.09
    0.4%
    767
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.21
    0.06
    740
    +0.09
    0.06
    696
    +0.08
    0.06
    Negative Logits
    deck
    -0.66
     inaug
    -0.63
     shack
    -0.63
     Puppet
    -0.61
     speeding
    -0.61
    frog
    -0.60
     accent
    -0.60
     sle
    -0.60
     Cavern
    -0.58
     sew
    -0.57
    POSITIVE LOGITS
    iblings
    0.81
    ographics
    0.79
    urrent
    0.78
    atched
    0.76
    esting
    0.76
    ufficient
    0.76
    umeric
    0.76
    ilus
    0.75
    anes
    0.74
    quished
    0.74
    Activations Density 0.332%

    No Known Activations