© 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. 3808
    Prev
    Next
    INDEX
    Explanations

    terminologies related to layers and structures in various contexts

    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
    642
    +0.11
    0.5%
    73
    +0.10
    0.5%
    678
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.11
    0.03
    640
    +0.10
    0.04
    326
    +0.10
    0.02
    Negative Logits
     Cruel
    -0.73
    Stats
    -0.72
     Chili
    -0.72
    Beer
    -0.72
     Butcher
    -0.72
    Teen
    -0.70
     Clubs
    -0.66
    Tax
    -0.66
     Slash
    -0.64
    wright
    -0.64
    POSITIVE LOGITS
     layers
    0.99
     opacity
    0.93
     structures
    0.84
     layer
    0.79
     opaque
    0.75
     formations
    0.75
     pockets
    0.73
     compress
    0.73
     pree
    0.73
     foundations
    0.72
    Activations Density 0.548%

    No Known Activations