© 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. 3754
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to data structures and algorithms

    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
    481
    +0.13
    0.6%
    497
    +0.11
    0.5%
    597
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.13
    0.05
    671
    +0.11
    0.05
    447
    +0.10
    0.08
    Negative Logits
     guiActiveUnfocused
    -0.80
    orum
    -0.72
    osterone
    -0.70
    veyard
    -0.69
     Caucus
    -0.69
     Crim
    -0.68
    ][/
    -0.68
     Tucker
    -0.68
     Barney
    -0.67
    ottage
    -0.67
    POSITIVE LOGITS
     derivative
    0.79
    omorphic
    0.76
     mapping
    0.73
    mode
    0.71
    onga
    0.70
    seq
    0.67
    agent
    0.66
    coded
    0.66
     elector
    0.66
    domain
    0.65
    Activations Density 1.544%

    No Known Activations