© 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. 8-RES_POST_32K-OAI
    11. 6996
    Prev
    Next
    INDEX
    Explanations

    time indicators and timestamps

    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
    121
    +0.10
    0.5%
    600
    +0.10
    0.5%
    297
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    104
    +0.10
    0.03
    501
    +0.10
    0.03
    Negative Logits
    ennes
    -0.77
    artney
    -0.76
    tests
    -0.72
    iffe
    -0.67
    ppard
    -0.67
     schemes
    -0.67
    ĺ
    -0.66
    )].
    -0.65
    ulates
    -0.65
    yrinth
    -0.65
    POSITIVE LOGITS
     IST
    0.99
     pm
    0.90
     Nanto
    0.88
     PM
    0.74
     JPM
    0.72
     AM
    0.72
     HF
    0.71
    Ham
    0.70
    BuyableInstoreAndOnline
    0.68
     IPM
    0.68
    Activations Density 0.146%

    No Known Activations