© 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. 27022
    Prev
    Next
    INDEX
    Explanations

    abbreviated identifiers or acronyms associated with entities or names

    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
    145
    +0.12
    0.5%
    177
    +0.10
    0.4%
    20
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.01
    406
    +0.10
    0.05
    232
    +0.09
    0.05
    Negative Logits
    phrine
    -0.72
    ators
    -0.67
    ISSION
    -0.66
    ESSION
    -0.64
    Stage
    -0.62
     Monarch
    -0.60
     Amend
    -0.58
     Zucker
    -0.58
     Issa
    -0.57
     compounded
    -0.57
    POSITIVE LOGITS
    DL
    1.01
    lock
    0.92
    LEY
    0.90
    leys
    0.89
    locks
    0.84
    ping
    0.84
    py
    0.83
    ley
    0.81
    ingly
    0.79
    KER
    0.79
    Activations Density 0.661%

    No Known Activations