© 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. 10-RES_POST_32K-OAI
    11. 32376
    Prev
    Next
    INDEX
    Explanations

    references to various types of systems

    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
    288
    +0.10
    0.5%
    31
    +0.10
    0.5%
    495
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.10
    0.04
    288
    +0.10
    0.04
    575
    +0.10
    0.04
    Negative Logits
    onga
    -0.75
    IELD
    -0.71
    tein
    -0.69
     earnest
    -0.66
    urous
    -0.64
    ãģ®å®
    -0.61
    joy
    -0.60
    ishable
    -0.60
    spell
    -0.59
    lihood
    -0.58
    POSITIVE LOGITS
    atics
    1.39
    atic
    1.13
    wide
    1.12
    atically
    1.10
    ically
    1.05
    ologies
    1.03
     integ
    1.01
    atical
    0.92
     administrator
    0.85
    ologically
    0.84
    Activations Density 0.182%

    No Known Activations