© 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. 5323
    Prev
    Next
    INDEX
    Explanations

    key concepts related to societal issues and priorities

    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
    686
    +0.10
    0.5%
    383
    +0.10
    0.4%
    747
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.10
    0.06
    288
    +0.10
    0.08
    540
    +0.10
    0.07
    Negative Logits
    odore
    -0.75
    teness
    -0.71
    ffen
    -0.69
    ameless
    -0.67
    ilipp
    -0.66
    azard
    -0.65
    agate
    -0.64
    asing
    -0.64
    ymes
    -0.63
    sterdam
    -0.63
    POSITIVE LOGITS
     amongst
    0.92
     among
    0.83
    stay
    0.82
     throughout
    0.81
     occurrence
    0.77
     nowadays
    0.74
     encount
    0.74
     whenever
    0.74
    leground
    0.73
     everywhere
    0.70
    Activations Density 0.636%

    No Known Activations