© 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. 4030
    Prev
    Next
    INDEX
    Explanations

    the concept of contrast or duality within 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
    623
    +0.12
    0.6%
    497
    +0.12
    0.5%
    541
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.12
    0.03
    623
    +0.12
    0.03
    473
    +0.10
    0.03
    Negative Logits
    ACTED
    -0.72
     Oath
    -0.64
     Firstly
    -0.61
    shed
    -0.61
    GROUND
    -0.61
    Accessory
    -0.60
    Firstly
    -0.60
    âĨij
    -0.59
     Miko
    -0.59
     siege
    -0.58
    POSITIVE LOGITS
    erella
    0.74
    vier
    0.74
    esthes
    0.71
    izon
    0.71
    escent
    0.70
    meyer
    0.70
    olk
    0.69
    swick
    0.68
    fish
    0.68
    viron
    0.66
    Activations Density 0.820%

    No Known Activations