© 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. 4052
    Prev
    Next
    INDEX
    Explanations

    references to entities that signal significant events or classifications within 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
    292
    +0.13
    0.6%
    683
    +0.10
    0.5%
    503
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.13
    0.06
    490
    +0.10
    0.05
    742
    +0.08
    0.04
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -1.00
    ĸļ
    -0.74
    ylum
    -0.71
    xs
    -0.64
     Attention
    -0.64
    MpServer
    -0.64
    âĹ¼
    -0.64
    /,
    -0.63
    azard
    -0.62
    ecycle
    -0.61
    POSITIVE LOGITS
     meanwhile
    0.68
     develops
    0.67
    sonian
    0.67
     pian
    0.64
     assures
    0.64
     melts
    0.63
     tells
    0.62
     scen
    0.62
     continues
    0.62
     is
    0.62
    Activations Density 0.924%

    No Known Activations