© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27814
    Prev
    Next
    INDEX
    Explanations

    references to health and safety concerns in relation to substances and policies

    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
    459
    +0.11
    0.5%
    309
    +0.10
    0.5%
    474
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.21
    288
    +0.10
    0.22
    40
    +0.10
    0.16
    Negative Logits
    cffffcc
    -0.90
     srfAttach
    -0.81
    Í
    -0.70
    ãĤ´ãĥ³
    -0.67
    ingo
    -0.66
    artifacts
    -0.64
    dry
    -0.64
    isexual
    -0.64
    ãĤ¦ãĤ¹
    -0.62
    NULL
    -0.61
    POSITIVE LOGITS
     afforded
    1.21
     seen
    1.16
     they
    1.09
     offered
    1.09
     we
    1.09
     shown
    1.09
     utilized
    1.08
     mentioned
    1.06
     allotted
    1.05
     depicted
    1.05
    Activations Density 4.340%

    No Known Activations