© 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. 3493
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of resetting or initializing processes or systems

    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
    660
    +0.11
    0.5%
    71
    +0.11
    0.5%
    391
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.11
    0.01
    523
    +0.11
    0.01
    654
    +0.11
    0.01
    Negative Logits
    isans
    -0.82
    66666666
    -0.73
    aghan
    -0.69
     firsthand
    -0.68
    olis
    -0.68
    erness
    -0.68
    orge
    -0.68
    irez
    -0.66
    sters
    -0.66
    Urban
    -0.64
    POSITIVE LOGITS
     countdown
    0.78
     reset
    0.76
     Negative
    0.75
     periodic
    0.75
     effectiveness
    0.73
    phrine
    0.71
     Password
    0.70
     deterrence
    0.69
     intervals
    0.68
     Repeat
    0.66
    Activations Density 0.128%

    No Known Activations