© 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. 29577
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    373
    +0.13
    0.6%
    293
    +0.12
    0.6%
    106
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.15
    608
    +0.12
    0.13
    393
    +0.09
    0.10
    Negative Logits
    classes
    -1.13
    types
    -1.12
    devices
    -1.09
    models
    -1.07
     highs
    -1.06
    issues
    -1.04
    rules
    -1.03
    values
    -1.03
    forts
    -1.03
    units
    -1.02
    POSITIVE LOGITS
     insistence
    0.96
     inability
    0.93
     refusal
    0.92
     allegation
    0.91
     acknowledgement
    0.91
     realization
    0.89
     unwillingness
    0.87
     acknowledgment
    0.87
     willingness
    0.86
     recognition
    0.85
    Activations Density 0.993%

    No Known Activations