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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5453
    Prev
    Next
    INDEX
    Explanations

    syntax related to functions and methods in programming

    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
    99
    +0.10
    0.5%
    593
    +0.10
    0.5%
    7
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    137
    +0.10
    0.01
    439
    +0.10
    0.01
    Negative Logits
    ysis
    -0.97
    ership
    -0.83
    angles
    -0.80
    ĪĴ
    -0.75
    backs
    -0.75
    anmar
    -0.74
    wagen
    -0.73
    tons
    -0.72
    inition
    -0.71
    hum
    -0.71
    POSITIVE LOGITS
    atively
    0.70
    Þ
    0.68
    CHAT
    0.65
    ³³³³³³³³
    0.62
     eleph
    0.61
    usha
    0.56
    ativity
    0.56
    oice
    0.55
    ittee
    0.55
     actionGroup
    0.55
    Activations Density 0.051%

    No Known Activations