© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4466
    Prev
    Next
    INDEX
    Explanations

    terms related to internal operations and governance

    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
    669
    +0.15
    0.7%
    159
    +0.10
    0.5%
    140
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.02
    669
    +0.10
    0.02
    505
    +0.09
    0.01
    Negative Logits
    akura
    -0.83
    schild
    -0.80
    akuya
    -0.77
    hiro
    -0.76
    agher
    -0.74
     Emin
    -0.70
    ancial
    -0.68
    atche
    -0.68
    esson
    -0.68
    adesh
    -0.68
    POSITIVE LOGITS
     corrid
    0.63
    ollen
    0.61
    chid
    0.60
     suspense
    0.59
    effic
    0.58
     sanct
    0.56
    "},
    0.55
    liction
    0.54
     auditor
    0.54
     balcon
    0.53
    Activations Density 0.057%

    No Known Activations