© 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. 3578
    Prev
    Next
    INDEX
    Explanations

    concepts related to fostering, nurturing, and cultivating various aspects of life

    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
    446
    +0.11
    0.5%
    33
    +0.10
    0.5%
    357
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.11
    0.03
    505
    +0.10
    0.01
    761
    +0.10
    0.02
    Negative Logits
     disapp
    -0.70
     timed
    -0.70
    ĪĴ
    -0.67
     disadvant
    -0.65
     Cinem
    -0.65
     laun
    -0.63
     screw
    -0.63
     goodbye
    -0.61
    ãĤ®
    -0.60
     tong
    -0.59
    POSITIVE LOGITS
    spir
    0.88
    uces
    0.85
    icultural
    0.82
    icum
    0.81
    IENT
    0.76
    ependence
    0.75
    amily
    0.72
    anoia
    0.70
    relations
    0.69
    aura
    0.68
    Activations Density 0.372%

    No Known Activations