© 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. 5162
    Prev
    Next
    INDEX
    Explanations

    elements related to URLs, web requests, and data management

    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
    505
    +0.09
    0.4%
    553
    +0.09
    0.4%
    425
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.09
    0.03
    548
    +0.09
    0.01
    556
    +0.09
    0.02
    Negative Logits
     capac
    -0.74
     disg
    -0.66
     Lup
    -0.63
     Peb
    -0.62
     reconc
    -0.61
     Rockets
    -0.60
     hyd
    -0.59
     defic
    -0.59
     Scorp
    -0.59
     Wizards
    -0.58
    POSITIVE LOGITS
     :
    1.79
     {:
    1.14
    \":
    1.04
     :(
    1.02
     :=
    1.02
    .:
    0.99
    ]:
    0.99
    ":
    0.98
    ':
    0.97
    =>
    0.94
    Activations Density 0.209%

    No Known Activations