© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    11. 4372
    Prev
    Next
    INDEX
    Explanations

    discussions around user feedback and complaints related to services or products

    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
    157
    +0.11
    0.5%
    505
    +0.10
    0.5%
    38
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.26
    70
    +0.10
    0.22
    608
    +0.10
    0.24
    Negative Logits
    Cooldown
    -0.65
    was
    -0.62
    olean
    -0.60
     belongs
    -0.59
    nostic
    -0.58
    availability
    -0.57
    Cub
    -0.57
    washer
    -0.57
     Kills
    -0.57
    sonian
    -0.56
    POSITIVE LOGITS
     themselves
    2.12
     their
    1.47
    selves
    1.44
    their
    1.36
     THEIR
    1.22
     Their
    1.18
    Their
    1.16
     collectively
    1.09
     careers
    1.05
     selves
    1.05
    Activations Density 9.816%

    No Known Activations