© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29648
    Prev
    Next
    INDEX
    Explanations

    references to the company Titan and its products or developments

    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
    549
    +0.13
    0.6%
    414
    +0.13
    0.6%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.05
    659
    +0.13
    0.03
    343
    +0.12
    0.02
    Negative Logits
    ntax
    -0.80
    cation
    -0.80
    rers
    -0.73
    rer
    -0.72
    enez
    -0.71
    lling
    -0.71
    bler
    -0.66
    dit
    -0.65
    lly
    -0.65
    mble
    -0.65
    POSITIVE LOGITS
    fall
    1.18
    omach
    1.08
    ics
    1.02
    ICS
    0.95
    ically
    0.95
    osphere
    0.92
    icum
    0.91
    ica
    0.91
    icals
    0.90
    osaurs
    0.90
    Activations Density 0.223%

    No Known Activations