© 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. 8-RES_POST_32K-OAI
    11. 7885
    Prev
    Next
    INDEX
    Explanations

    instances of the word "add" with varying activations suggesting a focus on the concept of addition or accumulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    +0.15
    0.7%
    276
    +0.10
    0.5%
    241
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.15
    0.04
    559
    +0.10
    0.02
    441
    +0.10
    0.02
    Negative Logits
     resemb
    -0.65
    Reloaded
    -0.64
     Mub
    -0.59
    æĪ¦
    -0.56
    æ©Ł
    -0.56
     correctly
    -0.55
    =-=-=-=-
    -0.55
     bounce
    -0.54
     front
    -0.54
    terday
    -0.54
    POSITIVE LOGITS
    ressing
    1.15
    ressed
    0.93
    resses
    0.93
    ict
    0.93
    iction
    0.92
    icted
    0.86
    ictions
    0.85
    icts
    0.85
    endum
    0.84
    ictive
    0.82
    Activations Density 0.171%

    No Known Activations