© 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. 31031
    Prev
    Next
    INDEX
    Explanations

    negative numerical or coded values

    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
    107
    +0.16
    0.7%
    373
    +0.12
    0.6%
    442
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.16
    0.02
    107
    +0.12
    0.02
    430
    +0.12
    0.02
    Negative Logits
     pione
    -0.72
     exagger
    -0.68
    Þ
    -0.63
     containment
    -0.63
     Paddock
    -0.62
     Hass
    -0.62
     Panic
    -0.61
     anomal
    -0.61
     redund
    -0.61
     Overs
    -0.61
    POSITIVE LOGITS
    generic
    1.00
    01
    0.99
    31
    0.98
    29
    0.94
    02
    0.94
    28
    0.92
    04
    0.92
    30
    0.91
    03
    0.90
    26
    0.90
    Activations Density 0.069%

    No Known Activations