© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3966
    Prev
    Next
    INDEX
    Explanations

    phrases describing weather phenomena and their effects

    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
    497
    +0.12
    0.5%
    683
    +0.11
    0.5%
    372
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.12
    0.13
    460
    +0.11
    0.06
    298
    +0.10
    0.07
    Negative Logits
    uthor
    -1.03
    UTH
    -0.82
    ¶æ
    -0.81
     LLP
    -0.80
    ALSE
    -0.79
     Selling
    -0.77
    farious
    -0.76
     Honour
    -0.76
     subcontract
    -0.76
    MQ
    -0.75
    POSITIVE LOGITS
     clouds
    0.93
     haze
    0.92
     cloudy
    0.90
     skies
    0.85
     eclipse
    0.84
     icy
    0.84
     storms
    0.83
     Clouds
    0.83
     rains
    0.82
     peaks
    0.81
    Activations Density 16.284%

    No Known Activations