© 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. 32315
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "V" in various contexts

    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
    395
    +0.11
    0.5%
    444
    +0.09
    0.4%
    37
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.04
    26
    +0.09
    0.02
    314
    +0.09
    0.00
    Negative Logits
     latitude
    -0.65
    ħĭ
    -0.61
     yourselves
    -0.60
     dumps
    -0.59
    ftime
    -0.58
     Slave
    -0.58
     Rasmussen
    -0.57
     awoken
    -0.57
    merce
    -0.56
     havens
    -0.55
    POSITIVE LOGITS
    incent
    1.12
    aries
    1.11
    itals
    1.11
    ARI
    1.03
    otes
    1.02
    oted
    1.01
    essel
    1.00
    isions
    0.99
    oldemort
    0.98
    engeance
    0.98
    Activations Density 0.189%

    No Known Activations