© 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. 3727
    Prev
    Next
    INDEX
    Explanations

    references to specific actions or commands in a technical or instructional context

    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
    533
    +0.10
    0.5%
    739
    +0.10
    0.4%
    298
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    739
    +0.10
    0.01
    471
    +0.10
    0.02
    326
    +0.09
    0.02
    Negative Logits
    )*
    -0.65
     Franken
    -0.64
     composition
    -0.64
    cially
    -0.61
     Carnage
    -0.61
    olo
    -0.60
     Tale
    -0.59
     specializing
    -0.59
     resear
    -0.59
     specialize
    -0.57
    POSITIVE LOGITS
    á½
    0.83
    INGTON
    0.79
    Ô
    0.76
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.75
    IRT
    0.74
    UGH
    0.74
    ãģ£
    0.73
    ãģĨ
    0.73
    è¦ļéĨĴ
    0.73
    ãģĦ
    0.73
    Activations Density 0.051%

    No Known Activations