© 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. 10-RES_POST_32K-OAI
    11. 27890
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and molecular structures related to phosphorus

    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
    450
    +0.14
    0.6%
    507
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.14
    0.02
    450
    +0.09
    0.01
    314
    +0.09
    -0.00
    Negative Logits
     Grimm
    -0.70
     Pengu
    -0.69
     Cinnamon
    -0.67
     Cosponsors
    -0.66
     witness
    -0.64
    CTV
    -0.63
    LAB
    -0.63
     Grizzlies
    -0.62
     Carib
    -0.60
     Concord
    -0.59
    POSITIVE LOGITS
    ory
    1.28
    orous
    1.11
    orescence
    1.06
    our
    1.03
    orus
    1.01
    orescent
    1.01
    ate
    0.99
    oin
    0.98
    arate
    0.98
    odies
    0.98
    Activations Density 0.095%

    No Known Activations