© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    references to technical processes and project management

    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
    420
    +0.12
    0.5%
    412
    +0.11
    0.5%
    560
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.12
    0.23
    511
    +0.11
    0.15
    601
    +0.11
    0.07
    Negative Logits
     Cele
    -0.76
     Quad
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
    ãĥ³ãĤ¸
    -0.65
     Gould
    -0.64
     Princess
    -0.63
     Duo
    -0.63
    WATCH
    -0.62
     Cloud
    -0.61
     Bomber
    -0.60
    POSITIVE LOGITS
    ahead
    0.68
    akh
    0.66
    events
    0.65
    attr
    0.65
    ÅŁ
    0.65
    estate
    0.65
    brance
    0.64
    vc
    0.63
    onen
    0.63
     inspectors
    0.63
    Activations Density 5.383%

    No Known Activations