© 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. 10-RES_POST_32K-OAI
    6. 29837
    Prev
    Next
    INDEX
    Explanations

    the term "special" in various contexts

    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
    314
    +0.11
    0.5%
    472
    +0.10
    0.5%
    710
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.11
    0.03
    345
    +0.10
    0.03
    729
    +0.10
    0.02
    Negative Logits
    amus
    -0.70
    76561
    -0.68
    anon
    -0.67
    nington
    -0.66
     Reloaded
    -0.63
    hari
    -0.63
     Twain
    -0.59
    conom
    -0.59
     Decay
    -0.58
     Reaper
    -0.58
    POSITIVE LOGITS
    ised
    1.36
    izations
    1.33
    ties
    1.33
    isations
    1.22
    ities
    1.12
    isation
    1.11
    ity
    1.11
    ising
    1.07
    ises
    1.03
    ized
    1.00
    Activations Density 0.114%

    No Known Activations