© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5003
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing actions and the inability to complete certain tasks

    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
    641
    +0.12
    0.5%
    383
    +0.11
    0.5%
    106
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.04
    411
    +0.11
    0.04
    620
    +0.10
    0.02
    Negative Logits
     Mub
    -0.68
    çīĪ
    -0.65
     Refugees
    -0.61
    abet
    -0.59
    tics
    -0.59
    Leaks
    -0.58
    rift
    -0.57
    bos
    -0.57
    tein
    -0.56
     Ic
    -0.55
    POSITIVE LOGITS
    yet
    0.85
     since
    0.79
    minded
    0.75
    icable
    0.74
    framework
    0.74
    ched
    0.73
     yet
    0.72
    icably
    0.70
     formally
    0.68
    ioned
    0.68
    Activations Density 0.407%

    No Known Activations