© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences or reflections

    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
    464
    +0.15
    0.7%
    745
    +0.12
    0.6%
    476
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.15
    0.05
    745
    +0.12
    0.11
    629
    +0.11
    0.07
    Negative Logits
    imeo
    -0.66
     Nieto
    -0.63
    edin
    -0.63
    enegger
    -0.60
     Webb
    -0.59
     disapp
    -0.58
     Campbell
    -0.57
     pressuring
    -0.56
     indexed
    -0.56
    ]."
    -0.55
    POSITIVE LOGITS
    eat
    0.73
     Flavoring
    0.72
    Parts
    0.68
    pmwiki
    0.68
    WAYS
    0.67
    yrics
    0.65
     nig
    0.64
    Origin
    0.63
     rye
    0.63
    hend
    0.63
    Activations Density 1.522%

    No Known Activations