© 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. 4034
    Prev
    Next
    INDEX
    Explanations

    specific names and terminologies associated with health and sports

    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
    71
    +0.14
    0.6%
    497
    +0.13
    0.6%
    760
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.14
    0.08
    46
    +0.13
    0.09
    521
    +0.11
    0.07
    Negative Logits
    irgin
    -0.75
    emetery
    -0.72
    icable
    -0.68
    ulous
    -0.65
    iscopal
    -0.64
    erness
    -0.64
    iation
    -0.63
    agascar
    -0.60
    ]),
    -0.60
    bsite
    -0.59
    POSITIVE LOGITS
    jong
    0.75
    Ĥİ
    0.73
    EStream
    0.73
     Neh
    0.71
    sky
    0.69
    wat
    0.68
    hid
    0.67
    NetMessage
    0.62
     Ramos
    0.61
    rin
    0.59
    Activations Density 3.455%

    No Known Activations