© 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. 3648
    Prev
    Next
    INDEX
    Explanations

    points of conflict or resolution in interpersonal relationships

    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
    684
    +0.11
    0.5%
    731
    +0.11
    0.5%
    543
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.14
    269
    +0.11
    0.12
    173
    +0.11
    0.10
    Negative Logits
     Entered
    -0.66
    updated
    -0.64
     updated
    -0.61
     Instruction
    -0.60
     shuffle
    -0.59
     Info
    -0.59
    must
    -0.57
     Offic
    -0.55
    juries
    -0.55
     Provided
    -0.55
    POSITIVE LOGITS
    ="#
    0.75
    retty
    0.75
     concess
    0.72
    uple
    0.67
    livion
    0.66
    ="/
    0.66
    ozy
    0.65
    aunder
    0.65
    SourceFile
    0.64
    ̶
    0.63
    Activations Density 6.659%

    No Known Activations