© 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. 4315
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinion and reasoning

    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
    481
    +0.14
    0.7%
    145
    +0.13
    0.6%
    207
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    691
    +0.14
    0.06
    618
    +0.13
    0.08
    282
    +0.10
    0.05
    Negative Logits
     clam
    -0.70
     thrive
    -0.67
     crunch
    -0.66
     hook
    -0.63
     amplify
    -0.62
     hop
    -0.61
     paw
    -0.61
    ucker
    -0.60
     charging
    -0.59
    "?
    -0.57
    POSITIVE LOGITS
    OIL
    0.73
    ãĤ©
    0.73
    azon
    0.70
    DEN
    0.69
    avia
    0.69
    anism
    0.66
    rod
    0.66
    âĵĺ
    0.65
    Constructed
    0.63
    iatrics
    0.62
    Activations Density 2.157%

    No Known Activations