© 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. 3699
    Prev
    Next
    INDEX
    Explanations

    programming functions and their structures

    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
    261
    +0.11
    0.5%
    367
    +0.09
    0.4%
    143
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    692
    +0.11
    0.01
    156
    +0.09
    0.01
    255
    +0.09
    0.01
    Negative Logits
     notebooks
    -0.75
    edes
    -0.72
    oln
    -0.68
    readable
    -0.67
    vag
    -0.67
    ebook
    -0.67
    sun
    -0.65
    cards
    -0.64
    reports
    -0.63
     Races
    -0.62
    POSITIVE LOGITS
     Collider
    0.76
    uate
    0.72
     rapport
    0.66
     reconcile
    0.66
     reconnect
    0.64
    adish
    0.63
     CTR
    0.62
     conjunction
    0.61
     distingu
    0.61
    iator
    0.61
    Activations Density 0.059%

    No Known Activations