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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4195
    Prev
    Next
    INDEX
    Explanations

    references to numerical values, particularly the word "two" in various contexts

    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
    527
    +0.10
    0.5%
    212
    +0.10
    0.5%
    534
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.10
    0.04
    408
    +0.10
    0.04
    223
    +0.10
    0.04
    Negative Logits
    igr
    -0.67
    tains
    -0.64
    isite
    -0.60
    itol
    -0.59
     sidx
    -0.58
    GM
    -0.58
    onica
    -0.57
    Adds
    -0.57
    oin
    -0.57
    loe
    -0.57
    POSITIVE LOGITS
     aren
    1.27
     are
    1.24
     weren
    1.20
     were
    1.14
     have
    1.05
     seem
    1.03
     cannot
    1.00
     differ
    0.97
     differed
    0.96
     emerged
    0.92
    Activations Density 0.106%

    No Known Activations