© 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. 5952
    Prev
    Next
    INDEX
    Explanations

    key-value pairs in a structured data format

    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
    556
    +0.11
    0.5%
    237
    +0.09
    0.4%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.01
    586
    +0.09
    0.01
    237
    +0.09
    0.01
    Negative Logits
    afety
    -0.74
    AMI
    -0.73
    emo
    -0.71
    ocom
    -0.70
    ccoli
    -0.70
    ongyang
    -0.69
    eeks
    -0.64
    DEF
    -0.64
    renheit
    -0.64
    INTON
    -0.62
    POSITIVE LOGITS
    ãĥķãĤ©
    0.68
     ende
    0.63
    ='
    0.62
    èĢħ
    0.61
    pse
    0.57
    vec
    0.56
     Scion
    0.56
     embed
    0.56
     whom
    0.55
     null
    0.55
    Activations Density 0.119%

    No Known Activations