© 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. 3800
    Prev
    Next
    INDEX
    Explanations

    acronyms and references to corporate entities and 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
    481
    +0.14
    0.7%
    217
    +0.12
    0.6%
    642
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.14
    0.06
    179
    +0.12
    0.06
    83
    +0.10
    0.06
    Negative Logits
    lang
    -0.80
    zan
    -0.78
    oln
    -0.72
    gyn
    -0.71
    alm
    -0.68
    ernel
    -0.66
    wer
    -0.66
    iq
    -0.65
    arn
    -0.65
    veland
    -0.63
    POSITIVE LOGITS
    istries
    0.67
    mobi
    0.67
    rawdownloadcloneembedreportprint
    0.64
    {"
    0.61
     validation
    0.58
     WARNING
    0.58
     Establishment
    0.57
    eele
    0.56
    aeus
    0.56
     itself
    0.56
    Activations Density 0.793%

    No Known Activations