© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3781
    Prev
    Next
    INDEX
    Explanations

    references to medical studies and academic citations

    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
    552
    +0.12
    0.5%
    745
    +0.11
    0.5%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.12
    0.04
    292
    +0.11
    0.04
    304
    +0.11
    0.04
    Negative Logits
    Enlarge
    -0.80
    -+-+
    -0.74
     Utilities
    -0.71
     Yourself
    -0.66
    WAR
    -0.66
     Relations
    -0.66
    ADVERTISEMENT
    -0.65
     Ariel
    -0.65
     Jung
    -0.65
     Transportation
    -0.63
    POSITIVE LOGITS
    croft
    0.67
    claw
    0.66
    cks
    0.65
    saf
    0.65
    azaki
    0.64
    advant
    0.64
    eneg
    0.63
    oubted
    0.63
    icating
    0.63
    oling
    0.62
    Activations Density 0.634%

    No Known Activations