© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3227
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or speech

    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
    9
    +0.11
    0.5%
    453
    +0.10
    0.5%
    545
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.11
    0.03
    94
    +0.10
    0.04
    380
    +0.10
    0.03
    Negative Logits
     laure
    -0.69
     fractures
    -0.67
     enrichment
    -0.67
     monuments
    -0.66
     markers
    -0.64
     campaigners
    -0.64
    escal
    -0.63
     nesting
    -0.63
    angering
    -0.61
     backdrop
    -0.61
    POSITIVE LOGITS
     directions
    0.77
    yip
    0.71
    escription
    0.69
    ĸļ
    0.68
    itatively
    0.68
    Stra
    0.67
    anus
    0.67
    legged
    0.66
    anu
    0.66
     Tup
    0.65
    Activations Density 0.320%

    No Known Activations