© 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. 3757
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to visual representation and spatial awareness

    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
    756
    +0.16
    0.7%
    745
    +0.15
    0.7%
    420
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    745
    +0.16
    0.28
    756
    +0.15
    0.27
    554
    +0.14
    0.30
    Negative Logits
    é¾
    -0.82
    âĢ¦]
    -0.68
    ]'
    -0.68
    )!
    -0.68
    ä¹
    -0.65
    ]."
    -0.64
     }}
    -0.64
    âĢ¦)
    -0.64
    åĬ
    -0.63
     myster
    -0.63
    POSITIVE LOGITS
    agonists
    0.85
    rolet
    0.79
    renheit
    0.79
    aste
    0.70
    orah
    0.66
    holes
    0.65
    urches
    0.65
    asting
    0.65
    rous
    0.64
    aque
    0.63
    Activations Density 21.794%

    No Known Activations