© 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. 5905
    Prev
    Next
    INDEX
    Explanations

    references to queens and related titles

    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
    352
    +0.10
    0.5%
    755
    +0.10
    0.4%
    740
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.10
    0.02
    117
    +0.10
    0.02
    99
    +0.09
    0.01
    Negative Logits
    ELL
    -0.84
    geist
    -0.83
    LER
    -0.75
    CAST
    -0.73
    lan
    -0.70
    dump
    -0.69
    schild
    -0.68
    ted
    -0.68
    ters
    -0.68
    STEM
    -0.66
    POSITIVE LOGITS
    istry
    0.96
    ĺħ
    0.86
    ĸļ
    0.78
    ignt
    0.78
    estate
    0.74
     patronage
    0.71
    doms
    0.70
    ival
    0.70
    shire
    0.70
     Guards
    0.69
    Activations Density 0.045%

    No Known Activations