© 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. 3310
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "last" along with temporal references

    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
    583
    +0.11
    0.5%
    318
    +0.11
    0.5%
    432
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.11
    0.04
    637
    +0.11
    0.04
    688
    +0.10
    0.02
    Negative Logits
    redients
    -0.85
    Twe
    -0.70
    REDACTED
    -0.69
    utherland
    -0.69
    icut
    -0.69
    idelines
    -0.68
    Lex
    -0.68
    elvet
    -0.67
    trl
    -0.66
    endix
    -0.65
    POSITIVE LOGITS
     millenn
    0.76
     chance
    0.72
     generation
    0.69
     possibility
    0.67
     likelihood
    0.66
     millisec
    0.66
    chance
    0.65
     opportun
    0.65
     subsistence
    0.63
     unaccount
    0.63
    Activations Density 1.512%

    No Known Activations