© 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. 4321
    Prev
    Next
    INDEX
    Explanations

    terms related to deterioration and degradation in various contexts

    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
    420
    +0.12
    0.5%
    77
    +0.10
    0.4%
    116
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    714
    +0.12
    0.02
    669
    +0.10
    0.02
    35
    +0.09
    0.02
    Negative Logits
    soDeliveryDate
    -0.97
     caveats
    -0.84
    soType
    -0.84
    isSpecialOrderable
    -0.77
     caveat
    -0.75
    ANA
    -0.73
    INFO
    -0.71
    Atlanta
    -0.71
    asking
    -0.70
    packed
    -0.70
    POSITIVE LOGITS
     decay
    0.88
     irreversible
    0.85
     corro
    0.80
    Ĥİ
    0.79
    gradation
    0.78
     commod
    0.78
     degradation
    0.77
     brittle
    0.77
     decom
    0.75
     decaying
    0.75
    Activations Density 0.290%

    No Known Activations