© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3645
    Prev
    Next
    INDEX
    Explanations

    references to financial costs or expenses

    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
    53
    +0.11
    0.5%
    340
    +0.10
    0.5%
    49
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    0.00
    426
    +0.10
    0.09
    94
    +0.09
    0.12
    Negative Logits
     advoc
    -0.77
     quarry
    -0.72
     COURT
    -0.72
     indo
    -0.69
     millenn
    -0.69
    å°Ĩ
    -0.68
     coffin
    -0.67
    Ĥİ
    -0.67
     charact
    -0.66
    ICO
    -0.66
    POSITIVE LOGITS
    vana
    0.79
    rous
    0.71
    addon
    0.70
    onies
    0.67
    ilic
    0.65
     Springfield
    0.64
    ¶
    0.64
     Shapiro
    0.62
    artz
    0.60
    psons
    0.60
    Activations Density 10.231%

    No Known Activations