Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 128k
    5. 0-ATT_128K-OAI
    6. 6453
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms, particularly Twitter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/GPT2-Small-OAI-v5-128k-attn-out-SAEs/v5_128k_layer_0
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    131,072
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_attn_out
    Hook Layer
    0
    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
    167
    +0.21
    1.6%
    339
    +0.19
    1.5%
    240
    +0.15
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.21
    0.01
    271
    +0.19
    0.01
    76
    +0.15
    0.01
    Negative Logits
    phrine
    -0.90
    lig
    -0.90
    leased
    -0.89
    heading
    -0.84
    taining
    -0.81
    leasing
    -0.76
    raham
    -0.75
     chemotherapy
    -0.72
    xual
    -0.72
    verend
    -0.72
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.91
     CTRL
    0.82
    ãĥ¼ãĥĨ
    0.80
     fixme
    0.80
    ãĥ£
    0.80
    alion
    0.79
    ãĥ¯ãĥ³
    0.78
    ãĥĻ
    0.76
    isSpecialOrderable
    0.74
    rers
    0.74
    Activations Density 0.008%

    No Known Activations