© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28769
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly focusing on the letter "W."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    659
    +0.20
    0.9%
    527
    +0.11
    0.5%
    567
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.20
    0.07
    18
    +0.11
    0.04
    99
    +0.10
    0.04
    Negative Logits
     psy
    -0.67
    enegger
    -0.65
     ascending
    -0.64
    puter
    -0.63
     182
    -0.58
     Celest
    -0.58
    stery
    -0.57
     descending
    -0.56
     Prelude
    -0.56
    quist
    -0.55
    POSITIVE LOGITS
    ASHINGTON
    1.21
    reck
    1.17
    OOD
    1.16
    idget
    1.14
    IRED
    1.10
    FU
    1.09
    ALK
    1.08
    TF
    1.07
    ookie
    1.07
    AV
    1.05
    Activations Density 0.110%

    No Known Activations