Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 128k
    5. 0-ATT_128K-OAI
    6. 13574
    Prev
    Next
    INDEX
    Explanations

    instances of the suffix 'ess' and related forms typically used to denote qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/GPT2-Small-OAI-v5-128k-attn-out-SAEs/v5_128k_layer_0
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    131,072
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_attn_out
    Hook Layer
    0
    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
    7
    +0.20
    1.4%
    271
    +0.19
    1.3%
    685
    +0.17
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.20
    0.01
    7
    +0.19
    0.01
    582
    +0.17
    0.01
    Negative Logits
     à¤
    -0.84
     Paradox
    -0.75
    fusc
    -0.70
     pse
    -0.68
     Emin
    -0.67
     Reincarn
    -0.66
     Citizen
    -0.65
     Bis
    -0.65
     Bosnia
    -0.65
     Sterling
    -0.64
    POSITIVE LOGITS
    yss
    0.89
    nces
    0.85
    inguished
    0.82
    iffe
    0.82
    cffff
    0.81
    OPLE
    0.75
    HER
    0.75
    perty
    0.75
    arios
    0.73
    ARCH
    0.73
    Activations Density 0.012%

    No Known Activations