© 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 EvalsExportsAPI 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. 28624
    Prev
    Next
    INDEX
    Explanations

    words associated with distrust or negative feelings

    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
    549
    +0.10
    0.5%
    127
    +0.10
    0.5%
    455
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.02
    288
    +0.10
    0.02
    314
    +0.10
    -0.00
    Negative Logits
    FactoryReloaded
    -0.71
     diction
    -0.61
     learners
    -0.60
     Slate
    -0.57
     rehearsal
    -0.57
     strands
    -0.56
     darts
    -0.56
     Sparrow
    -0.55
     flashes
    -0.55
    fields
    -0.54
    POSITIVE LOGITS
    illation
    1.42
    anced
    1.41
    ancing
    1.28
    aste
    1.22
    illery
    1.18
    iller
    1.17
    illing
    1.16
    ributes
    1.13
    rub
    1.10
    antly
    1.08
    Activations Density 0.095%

    No Known Activations