© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    processes and actions related to collaboration and cooperation

    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
    27
    +0.11
    0.5%
    66
    +0.11
    0.5%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.11
    0.05
    27
    +0.11
    0.04
    3
    +0.11
    0.05
    Negative Logits
    itatively
    -0.69
    isu
    -0.68
    "]=>
    -0.64
    "))
    -0.63
    NRS
    -0.63
    "],"
    -0.62
    iffe
    -0.62
    iggs
    -0.61
    done
    -0.61
    ord
    -0.61
    POSITIVE LOGITS
     margins
    0.68
     Bid
    0.65
    ecycle
    0.63
     margin
    0.61
    charges
    0.60
     guise
    0.59
     Arrows
    0.59
     Waves
    0.58
     Carnival
    0.57
     Rebirth
    0.57
    Activations Density 1.217%

    No Known Activations