© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5350
    Prev
    Next
    INDEX
    Explanations

    words related to social relationships and connections

    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
    496
    +0.11
    0.5%
    283
    +0.10
    0.5%
    714
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.08
    284
    +0.10
    0.06
    701
    +0.09
    0.05
    Negative Logits
    cano
    -0.66
     ABE
    -0.63
    ptions
    -0.60
    lems
    -0.59
    STON
    -0.58
     background
    -0.57
    vernment
    -0.57
     Unle
    -0.55
    ittal
    -0.54
    cox
    -0.54
    POSITIVE LOGITS
    oday
    1.18
    ools
    1.14
    rop
    1.10
    opia
    1.09
    rix
    1.08
    ypes
    1.08
    imes
    1.08
    rophe
    1.05
    ronics
    1.03
    hesis
    1.03
    Activations Density 0.689%

    No Known Activations