© 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. 27367
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations related to follow-up 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
    679
    +0.15
    0.7%
    290
    +0.11
    0.5%
    105
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.15
    0.03
    435
    +0.11
    0.01
    665
    +0.10
    0.02
    Negative Logits
     Scotia
    -0.78
    ãĥĨãĤ£
    -0.73
     Fey
    -0.69
    lux
    -0.66
    EStreamFrame
    -0.65
     Unic
    -0.62
    cin
    -0.61
     Bett
    -0.61
     CES
    -0.60
    cit
    -0.60
    POSITIVE LOGITS
    ingly
    0.91
    ings
    0.86
     closely
    0.84
    ership
    0.81
    SHIP
    0.74
    ents
    0.74
     logically
    0.73
    eth
    0.73
    masters
    0.72
    enance
    0.72
    Activations Density 0.148%

    No Known Activations