© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    terms related to reliability and data credibility

    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
    625
    +0.12
    0.6%
    460
    +0.12
    0.5%
    608
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    625
    +0.12
    0.03
    609
    +0.12
    0.03
    200
    +0.10
    0.03
    Negative Logits
    ĸļ
    -0.88
    ovember
    -0.80
    ModLoader
    -0.78
    umblr
    -0.73
    uliffe
    -0.73
    emi
    -0.72
    ansk
    -0.69
    xual
    -0.69
    lda
    -0.69
    rican
    -0.68
    POSITIVE LOGITS
     reliable
    1.19
     reliably
    1.02
     trustworthy
    0.90
     reliability
    0.76
     accur
    0.75
     accurate
    0.72
     unreliable
    0.72
     reprodu
    0.71
     corrobor
    0.71
     competent
    0.70
    Activations Density 0.326%

    No Known Activations