© 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 EvalsExportsAPI 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. 31036
    Prev
    Next
    INDEX
    Explanations

    references to information and evidence related to crimes

    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
    756
    +0.14
    0.6%
    189
    +0.13
    0.6%
    114
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.14
    0.10
    575
    +0.13
    0.11
    698
    +0.12
    0.10
    Negative Logits
     rejoice
    -0.73
    ourge
    -0.73
    ometimes
    -0.72
    iversity
    -0.65
    obyl
    -0.65
    cffff
    -0.65
     dwell
    -0.65
    reprene
    -0.65
    eworld
    -0.64
     wast
    -0.63
    POSITIVE LOGITS
     incrim
    1.38
     pertinent
    1.15
     relating
    1.14
     identifying
    1.08
     indicating
    1.06
     confirming
    1.03
     tying
    1.02
     relevant
    1.01
     proving
    1.00
     pertaining
    0.99
    Activations Density 1.104%

    No Known Activations