© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4170
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and social justice issues

    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
    164
    +0.11
    0.5%
    279
    +0.11
    0.5%
    102
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    0.03
    446
    +0.11
    0.04
    164
    +0.10
    0.04
    Negative Logits
     Meteor
    -0.75
     Orchestra
    -0.69
    ãĥĵ
    -0.64
    etsu
    -0.63
     Sect
    -0.62
     è£ıè¦ļéĨĴ
    -0.61
     Locations
    -0.60
    arbon
    -0.59
     Reported
    -0.59
    senal
    -0.58
    POSITIVE LOGITS
    idth
    0.76
     laundry
    0.74
    fashioned
    0.70
    istically
    0.69
     fingert
    0.69
    berries
    0.68
    ylum
    0.68
     Turing
    0.66
    Merit
    0.63
    UGC
    0.62
    Activations Density 0.808%

    No Known Activations