© 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. 7662
    Prev
    Next
    INDEX
    Explanations

    instances of possessive pronouns or ownership expressions

    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
    420
    +0.12
    0.6%
    167
    +0.10
    0.5%
    579
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    579
    +0.12
    0.02
    637
    +0.10
    0.02
    148
    +0.09
    0.02
    Negative Logits
    PsyNetMessage
    -0.86
     partName
    -0.75
     Handling
    -0.70
    ļéĨĴ
    -0.69
    ħĭ
    -0.67
    ANS
    -0.66
     Enhancement
    -0.64
    Introduced
    -0.63
     Prosecut
    -0.63
    çīĪ
    -0.63
    POSITIVE LOGITS
    clock
    1.33
    Clock
    0.89
    course
    0.84
    ahu
    0.76
     clock
    0.74
    Leary
    0.74
    eries
    0.73
     madness
    0.72
    ween
    0.69
    elines
    0.68
    Activations Density 0.146%

    No Known Activations