© 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. 31216
    Prev
    Next
    INDEX
    Explanations

    conjunctions and linking phrases indicating ongoing or sequential actions

    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
    545
    +0.10
    0.5%
    203
    +0.10
    0.5%
    603
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.10
    0.06
    451
    +0.10
    0.04
    682
    +0.10
    0.04
    Negative Logits
    idth
    -0.79
     Explicit
    -0.69
    iosyncr
    -0.69
    aws
    -0.67
    clips
    -0.65
     emulation
    -0.65
    rio
    -0.65
     Advertisement
    -0.65
     Views
    -0.63
    ync
    -0.63
    POSITIVE LOGITS
     sentenced
    1.14
     interrogated
    1.12
     convicted
    1.08
     flown
    1.07
     fined
    1.07
     beaten
    1.00
     deported
    0.99
     jailed
    0.98
     detained
    0.98
     imprisoned
    0.97
    Activations Density 0.502%

    No Known Activations