© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3208
    Prev
    Next
    INDEX
    Explanations

    mentions of groups, organizations, and collective entities

    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
    169
    +0.14
    0.7%
    513
    +0.10
    0.5%
    752
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.14
    0.12
    83
    +0.10
    0.07
    513
    +0.09
    0.08
    Negative Logits
     surge
    -0.70
     rises
    -0.69
    ]}
    -0.69
     surges
    -0.68
    '>
    -0.67
     ambush
    -0.67
     thirst
    -0.67
     disappearing
    -0.65
    agogue
    -0.65
    ?'
    -0.64
    POSITIVE LOGITS
     additionally
    0.72
     interpol
    0.71
     scen
    0.69
     unpublished
    0.69
     respectively
    0.68
    sonian
    0.67
    .).
    0.67
    ospons
    0.67
    note
    0.66
     certific
    0.66
    Activations Density 6.881%

    No Known Activations