© 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. 4017
    Prev
    Next
    INDEX
    Explanations

    phrases related to control and memory management

    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
    573
    +0.12
    0.5%
    188
    +0.10
    0.4%
    333
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    573
    +0.12
    0.06
    654
    +0.10
    0.05
    456
    +0.10
    0.04
    Negative Logits
    ãĤ¶
    -0.87
    Bal
    -0.71
    ARB
    -0.68
    ãĥŁ
    -0.68
    Pir
    -0.66
    angan
    -0.66
    ãĥīãĥ©
    -0.65
    ãĤ¦ãĤ¹
    -0.65
    clad
    -0.64
    ãĤ´ãĥ³
    -0.63
    POSITIVE LOGITS
     rede
    0.68
     bets
    0.64
     introdu
    0.64
     wart
    0.60
    names
    0.60
     entries
    0.60
     wheelchair
    0.58
     grabs
    0.58
     ado
    0.58
     wont
    0.58
    Activations Density 1.844%

    No Known Activations