© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3494
    Prev
    Next
    INDEX
    Explanations

    references to significant sports awards or achievements

    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
    71
    +0.18
    0.8%
    362
    +0.11
    0.5%
    423
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.18
    0.14
    86
    +0.11
    0.20
    423
    +0.10
    0.14
    Negative Logits
    Poké
    -0.66
     Sut
    -0.64
     Hau
    -0.63
     comprises
    -0.63
     Bulk
    -0.63
     loudspe
    -0.63
    uum
    -0.63
    Roaming
    -0.61
    Mech
    -0.60
     survives
    -0.59
    POSITIVE LOGITS
     sqor
    0.81
    malink
    0.78
     firsthand
    0.73
     unsus
    0.72
     anew
    0.67
     rebuke
    0.66
     rebell
    0.65
    zn
    0.64
     culminating
    0.62
    enhagen
    0.62
    Activations Density 20.840%

    No Known Activations