© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3666
    Prev
    Next
    INDEX
    Explanations

    phrases related to confrontation and readiness for action

    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
    738
    +0.09
    0.4%
    445
    +0.09
    0.4%
    474
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.09
    0.04
    47
    +0.09
    0.03
    666
    +0.09
    0.02
    Negative Logits
    Downloadha
    -1.00
     multiplier
    -0.68
     contribut
    -0.68
     dogged
    -0.65
     persisted
    -0.65
     anim
    -0.65
     pract
    -0.65
     chirop
    -0.64
     retained
    -0.64
     pse
    -0.63
    POSITIVE LOGITS
    ãĤ¼ãĤ¦ãĤ¹
    0.85
    edo
    0.78
     tomorrow
    0.73
    uberty
    0.69
    ihilation
    0.68
    ieg
    0.68
    LEASE
    0.68
     ASAP
    0.68
    ETA
    0.67
    ocene
    0.67
    Activations Density 0.537%

    No Known Activations