© 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. 3697
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    574
    +0.12
    0.5%
    427
    +0.10
    0.5%
    29
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.12
    0.09
    751
    +0.10
    0.09
    737
    +0.10
    0.09
    Negative Logits
    wegian
    -0.87
    emort
    -0.69
    onyms
    -0.68
    Code
    -0.68
     elig
    -0.67
     locals
    -0.67
     mentors
    -0.66
    nom
    -0.66
    availability
    -0.66
    codes
    -0.64
    POSITIVE LOGITS
    "}
    0.81
    .")
    0.73
    ————————————————
    0.73
    Lago
    0.70
     [&
    0.69
     Volcano
    0.68
    ||||
    0.65
    ————————
    0.64
    flation
    0.64
    osaurus
    0.63
    Activations Density 1.239%

    No Known Activations