© 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. 3467
    Prev
    Next
    INDEX
    Explanations

    political affiliations and party references

    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
    745
    +0.14
    0.6%
    185
    +0.11
    0.5%
    709
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.14
    0.18
    326
    +0.11
    0.12
    767
    +0.09
    0.07
    Negative Logits
     accord
    -0.71
     ingest
    -0.66
     ÂŃ
    -0.65
    taboola
    -0.65
    ilaterally
    -0.64
    soever
    -0.64
     Chero
    -0.63
    approximately
    -0.62
     Tec
    -0.61
    appropriately
    -0.61
    POSITIVE LOGITS
     meanwhile
    0.68
    ILS
    0.65
    hin
    0.63
    Gam
    0.60
    hov
    0.60
    ibl
    0.59
    resy
    0.59
     BL
    0.58
    cles
    0.58
    bra
    0.57
    Activations Density 7.067%

    No Known Activations