© 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. 30954
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of dissatisfaction

    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
    102
    +0.15
    0.7%
    277
    +0.11
    0.5%
    377
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.15
    0.11
    566
    +0.11
    0.08
    55
    +0.11
    0.08
    Negative Logits
     fracture
    -0.73
     BaseType
    -0.62
     sqor
    -0.62
     decay
    -0.60
     Outbreak
    -0.59
     Roe
    -0.59
     landsl
    -0.58
     mitigation
    -0.58
     TBD
    -0.58
    mere
    -0.57
    POSITIVE LOGITS
     sure
    1.27
     thrilled
    1.09
     pleased
    1.07
     expecting
    1.06
     aware
    1.06
     surprised
    1.05
     happy
    1.04
     impressed
    1.04
     satisfied
    1.04
     amused
    1.00
    Activations Density 0.396%

    No Known Activations