© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3940
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical information

    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
    278
    +0.12
    0.5%
    333
    +0.10
    0.5%
    27
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.12
    0.05
    462
    +0.10
    0.04
    272
    +0.10
    0.04
    Negative Logits
     sqor
    -0.79
     Adin
    -0.77
    ogle
    -0.68
    ailable
    -0.66
    ĪĴ
    -0.65
    laden
    -0.63
    edo
    -0.61
    ÙIJ
    -0.61
    ullah
    -0.61
    icz
    -0.60
    POSITIVE LOGITS
    âĦ¢:
    0.67
    bourg
    0.67
    keleton
    0.64
     Venezuel
    0.64
    ERY
    0.62
    photo
    0.62
    iors
    0.59
     Hebdo
    0.59
    ateurs
    0.58
     Prix
    0.57
    Activations Density 0.444%

    No Known Activations