© 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. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4757
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate understanding, decisions, or actions taken by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    702
    +0.12
    0.6%
    425
    +0.11
    0.5%
    624
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.12
    0.11
    665
    +0.11
    0.11
    184
    +0.10
    0.04
    Negative Logits
    eers
    -0.76
     understandably
    -0.67
    Fail
    -0.64
     flourish
    -0.63
    umblr
    -0.62
     predictably
    -0.60
    aminer
    -0.60
    Eva
    -0.59
    sis
    -0.57
    ?),
    -0.57
    POSITIVE LOGITS
     constituent
    0.79
     myself
    0.75
     "#
    0.70
     personally
    0.66
     Mehran
    0.65
     constituents
    0.64
    %"
    0.63
    poke
    0.63
     Paddock
    0.61
    oan
    0.59
    Activations Density 2.838%

    No Known Activations