© 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. 3986
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing certainty and factual statements

    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
    762
    +0.12
    0.5%
    56
    +0.11
    0.5%
    227
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.12
    0.02
    213
    +0.11
    0.01
    607
    +0.11
    0.02
    Negative Logits
    BuyableInstoreAndOnline
    -0.89
    ohm
    -0.79
    ific
    -0.78
    ãĤ´ãĥ³
    -0.74
     sidx
    -0.74
    arms
    -0.72
    isSpecialOrderable
    -0.71
    icter
    -0.70
    DOS
    -0.68
    ibaba
    -0.67
    POSITIVE LOGITS
     anatomy
    0.68
     intersect
    0.65
     postp
    0.64
     mov
    0.63
     composition
    0.63
     ants
    0.63
     detain
    0.61
     peg
    0.61
     disconnect
    0.61
     juxtap
    0.60
    Activations Density 0.420%

    No Known Activations