© 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. 4455
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions, particularly focusing on appending data structures or elements

    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
    +0.13
    0.6%
    236
    +0.11
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.13
    0.01
    569
    +0.11
    0.01
    678
    +0.10
    0.01
    Negative Logits
    SEA
    -0.74
    lift
    -0.70
    âĸ¬
    -0.69
    ģ«
    -0.69
    nit
    -0.68
    ipeg
    -0.67
    Score
    -0.64
    cloud
    -0.63
    pert
    -0.62
    Flow
    -0.62
    POSITIVE LOGITS
     skelet
    0.80
     Invalid
    0.77
     Bib
    0.67
    gypt
    0.67
    ectomy
    0.66
     Sack
    0.66
    nces
    0.65
     Psy
    0.65
    olescent
    0.64
    */(
    0.64
    Activations Density 0.080%

    No Known Activations