© 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. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4119
    Prev
    Next
    INDEX
    Explanations

    elements related to gaming and media references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    672
    +0.12
    0.6%
    515
    +0.10
    0.5%
    709
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    0.01
    515
    +0.10
    0.03
    679
    +0.10
    0.04
    Negative Logits
     ener
    -0.74
     urgent
    -0.70
     actionGroup
    -0.70
     resent
    -0.69
     poisoned
    -0.69
     learnt
    -0.69
     distance
    -0.66
    cedented
    -0.66
     prey
    -0.65
     res
    -0.64
    POSITIVE LOGITS
     Bleach
    1.00
     Encyclopedia
    0.85
     Nickel
    0.83
    pmwiki
    0.78
    infeld
    0.75
    ikuman
    0.74
    tymology
    0.74
     Sponge
    0.74
     Gilmore
    0.72
    ucket
    0.71
    Activations Density 0.407%

    No Known Activations