© 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. 3695
    Prev
    Next
    INDEX
    Explanations

    actions and verbs indicating various forms of managing, understanding, and manipulating situations or objects

    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
    33
    +0.10
    0.5%
    218
    +0.09
    0.4%
    237
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.09
    754
    +0.09
    0.10
    762
    +0.09
    0.12
    Negative Logits
     Maid
    -0.65
     aug
    -0.64
    idia
    -0.61
     Inner
    -0.61
     Kaiser
    -0.60
     Mech
    -0.60
     Assembly
    -0.58
     Metro
    -0.58
     Catalyst
    -0.57
    quel
    -0.56
    POSITIVE LOGITS
     destro
    0.97
     offend
    0.87
     trave
    0.87
     thirst
    0.84
    otle
    0.78
    awed
    0.78
    enance
    0.77
     awa
    0.76
     intimidate
    0.76
     tremend
    0.76
    Activations Density 2.887%

    No Known Activations