© 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. 3910
    Prev
    Next
    INDEX
    Explanations

    references to various crises and management in society

    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
    594
    +0.12
    0.6%
    51
    +0.11
    0.5%
    77
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.12
    0.02
    594
    +0.11
    0.02
    132
    +0.10
    0.02
    Negative Logits
     slices
    -0.75
    oso
    -0.67
    aves
    -0.64
     precincts
    -0.64
    rahim
    -0.63
    ameless
    -0.62
    friends
    -0.61
    cks
    -0.61
     slice
    -0.61
    riks
    -0.61
    POSITIVE LOGITS
     Despair
    0.80
     spir
    0.79
     predic
    0.77
     Anxiety
    0.75
     exacerbated
    0.74
     dire
    0.73
     engulf
    0.73
     culminating
    0.71
    sit
    0.70
     backdrop
    0.69
    Activations Density 0.299%

    No Known Activations