© 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. 4482
    Prev
    Next
    INDEX
    Explanations

    sentences containing personal experiences or interactions involving emotional responses

    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
    760
    +0.14
    0.6%
    471
    +0.10
    0.5%
    670
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.14
    0.23
    148
    +0.10
    0.24
    346
    +0.09
    0.24
    Negative Logits
     heel
    -0.63
     NCAA
    -0.63
     Attention
    -0.62
    incinnati
    -0.58
    ammy
    -0.57
    taboola
    -0.57
    ithing
    -0.56
     projector
    -0.56
     println
    -0.56
    ppings
    -0.55
    POSITIVE LOGITS
    ????????
    0.75
    âĢ
    0.73
    "?
    0.69
    ?!"
    0.69
     Profession
    0.67
    pter
    0.66
    Particip
    0.65
    ?'
    0.65
    erity
    0.65
     ðŁij
    0.64
    Activations Density 10.876%

    No Known Activations