© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29604
    Prev
    Next
    INDEX
    Explanations

    technical terms related to hardware security and modules

    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
    373
    +0.22
    1.0%
    314
    +0.15
    0.7%
    222
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.22
    -0.01
    158
    +0.15
    0.06
    326
    +0.09
    0.10
    Negative Logits
     territ
    -0.76
     mosqu
    -0.74
     soar
    -0.72
     renew
    -0.72
     happ
    -0.70
     toget
    -0.69
     leisure
    -0.66
     experien
    -0.66
     renewal
    -0.66
     spa
    -0.66
    POSITIVE LOGITS
    _(
    1.70
    ._
    1.07
    #
    1.03
    _.
    0.94
    #$#$
    0.91
    ##
    0.91
    ():
    0.89
    âĢ
    0.88
    _
    0.87
    /(
    0.84
    Activations Density 1.403%

    No Known Activations