© 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. 3863
    Prev
    Next
    INDEX
    Explanations

    concepts related to resource management or recycling

    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
    459
    +0.21
    1.0%
    497
    +0.17
    0.8%
    218
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.21
    0.26
    1
    +0.17
    0.11
    92
    +0.13
    0.13
    Negative Logits
    rosse
    -0.81
    terday
    -0.76
    owship
    -0.74
    Ń·
    -0.70
    unta
    -0.67
    ucha
    -0.63
     deputies
    -0.63
    jury
    -0.62
    vs
    -0.59
    ighting
    -0.59
    POSITIVE LOGITS
    endif
    0.70
    cyclopedia
    0.67
     anyways
    0.66
     perspective
    0.65
     perverse
    0.65
     GOODMAN
    0.65
    erker
    0.64
    ĸļ
    0.62
    berra
    0.61
     endif
    0.60
    Activations Density 12.323%

    No Known Activations