© 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. 3732
    Prev
    Next
    INDEX
    Explanations

    references to political or corporate accountability and scrutiny

    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
    401
    +0.11
    0.5%
    621
    +0.10
    0.5%
    172
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.11
    0.04
    621
    +0.10
    0.05
    147
    +0.10
    0.05
    Negative Logits
    èĢħ
    -0.67
    ascript
    -0.67
    itect
    -0.65
    士
    -0.64
     è£ıç
    -0.64
    iem
    -0.63
    =~=~
    -0.61
    ©¶æ
    -0.61
    Scene
    -0.61
    ajor
    -0.61
    POSITIVE LOGITS
     thereof
    0.73
     horm
    0.73
     thereto
    0.65
     therein
    0.60
     outl
    0.60
     giveaways
    0.60
    ravings
    0.60
    SPONSORED
    0.58
    âĢ¦.
    0.57
     downright
    0.57
    Activations Density 4.436%

    No Known Activations