© 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. 3079
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to programming and software development

    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
    +0.23
    1.1%
    309
    +0.09
    0.4%
    534
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    745
    +0.23
    0.20
    624
    +0.09
    0.13
    335
    +0.08
    0.17
    Negative Logits
     lashes
    -0.72
    083
    -0.68
    soType
    -0.61
    antha
    -0.61
     applause
    -0.60
    ãĤ¢ãĥ«
    -0.60
    ãĤ®
    -0.59
    ]."
    -0.59
    ãĥ¼ãĥĨ
    -0.59
     repeating
    -0.59
    POSITIVE LOGITS
    Prim
    0.67
    nance
    0.66
    ateurs
    0.63
     resemb
    0.62
    JV
    0.62
     Âł Âł Âł Âł
    0.62
     specialized
    0.61
     Templ
    0.60
    ghai
    0.60
     DRM
    0.60
    Activations Density 8.426%

    No Known Activations