© 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. 4982
    Prev
    Next
    INDEX
    Explanations

    instances of the concept of "paying a price" or the costs associated with various situations

    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
    420
    +0.14
    0.7%
    374
    +0.12
    0.5%
    252
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.14
    0.04
    439
    +0.12
    0.03
    386
    +0.11
    0.04
    Negative Logits
    dayName
    -0.85
    FTWARE
    -0.83
    oday
    -0.81
    Dub
    -0.78
    uggest
    -0.76
    SpaceEngineers
    -0.69
    intend
    -0.65
    TPPStreamerBot
    -0.63
    ocument
    -0.63
    pmwiki
    -0.63
    POSITIVE LOGITS
     sacrifice
    0.83
     inflicted
    0.81
     casualties
    0.77
     sacrifices
    0.74
     incurred
    0.69
     wounds
    0.69
     inflicting
    0.68
     deterrence
    0.67
     dearly
    0.67
     costly
    0.67
    Activations Density 0.457%

    No Known Activations