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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5560
    Prev
    Next
    INDEX
    Explanations

    references to volume numbers in a series or publication

    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
    314
    +0.11
    0.5%
    649
    +0.11
    0.5%
    319
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.11
    0.02
    48
    +0.11
    0.02
    558
    +0.10
    0.02
    Negative Logits
    riad
    -0.81
    nesses
    -0.64
     Blessed
    -0.63
    olph
    -0.63
    éĹĺ
    -0.63
     responsibility
    -0.60
    naire
    -0.60
    âķIJâķIJ
    -0.60
     Arbor
    -0.60
     Preferred
    -0.59
    POSITIVE LOGITS
    atile
    1.16
    atility
    1.13
    untary
    0.99
    oided
    0.87
    undai
    0.84
    ¹
    0.80
    ulet
    0.79
    trak
    0.77
    ccording
    0.77
    cow
    0.77
    Activations Density 0.104%

    No Known Activations