© 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. 5173
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and accountability

    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
    66
    +0.11
    0.5%
    452
    +0.10
    0.4%
    157
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.12
    351
    +0.10
    0.07
    728
    +0.10
    0.03
    Negative Logits
    cium
    -0.67
    Contin
    -0.67
    AX
    -0.66
    oids
    -0.59
    enium
    -0.59
    otropic
    -0.59
    ombat
    -0.58
    ibu
    -0.57
    utt
    -0.57
    iband
    -0.56
    POSITIVE LOGITS
     theirs
    1.86
     hers
    1.67
     yours
    1.51
     ours
    1.49
     mine
    1.31
    his
    1.25
    their
    1.22
    your
    1.18
     his
    1.17
     your
    1.12
    Activations Density 3.047%

    No Known Activations