© 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. 4033
    Prev
    Next
    INDEX
    Explanations

    references to principles and values concerning equality and free speech

    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
    159
    +0.11
    0.5%
    548
    +0.11
    0.5%
    384
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.11
    0.02
    655
    +0.11
    0.01
    516
    +0.10
    0.01
    Negative Logits
     Panda
    -0.74
    ebin
    -0.73
    ipel
    -0.70
    abad
    -0.63
     Haku
    -0.63
     heels
    -0.63
     dumps
    -0.63
    pload
    -0.61
     Craw
    -0.60
     ponds
    -0.59
    POSITIVE LOGITS
    ciples
    0.84
    rence
    0.81
    ©¶æ
    0.80
    cellence
    0.71
     guiActiveUnfocused
    0.69
    actionDate
    0.67
    love
    0.66
    cipled
    0.66
    gression
    0.66
     Recomm
    0.64
    Activations Density 0.169%

    No Known Activations