© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4004
    Prev
    Next
    INDEX
    Explanations

    specific names of political figures and their related context

    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
    469
    +0.12
    0.5%
    429
    +0.10
    0.5%
    684
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.12
    0.13
    429
    +0.10
    0.07
    22
    +0.10
    0.10
    Negative Logits
    lease
    -1.03
    endars
    -0.92
     Warehouse
    -0.89
    oho
    -0.89
    thouse
    -0.82
     Celebration
    -0.81
    mercial
    -0.79
    assadors
    -0.77
    tainment
    -0.75
    minster
    -0.75
    POSITIVE LOGITS
    ccording
    0.87
     trait
    0.82
     comparable
    0.81
     averages
    0.80
     comparisons
    0.76
     composite
    0.75
     variation
    0.75
     traits
    0.74
     differences
    0.74
     Comparison
    0.74
    Activations Density 18.245%

    No Known Activations