© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29380
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that convey emotional or physical states

    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
    314
    +0.32
    1.5%
    459
    +0.15
    0.7%
    15
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.32
    0.06
    159
    +0.15
    0.05
    288
    +0.10
    0.08
    Negative Logits
     DRAG
    -0.76
     Grill
    -0.69
     Haram
    -0.69
     MAC
    -0.67
     Sparkle
    -0.65
     [|
    -0.65
     Slug
    -0.63
     CTR
    -0.63
    Downloadha
    -0.62
     TAM
    -0.62
    POSITIVE LOGITS
    ness
    1.80
    est
    1.71
    nesses
    1.65
    ening
    1.47
    itude
    1.40
    eness
    1.37
    ener
    1.31
    itudes
    1.29
    er
    1.27
    itudinal
    1.22
    Activations Density 0.917%

    No Known Activations