© 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. 5329
    Prev
    Next
    INDEX
    Explanations

    references to future timeframes or events

    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
    339
    +0.11
    0.5%
    731
    +0.11
    0.5%
    706
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.11
    0.02
    183
    +0.11
    0.01
    731
    +0.09
    0.01
    Negative Logits
    wright
    -0.86
    olkien
    -0.79
    uca
    -0.79
    ooters
    -0.77
    osate
    -0.76
    urtles
    -0.75
    ulhu
    -0.75
    ertodd
    -0.74
    gor
    -0.72
    aundering
    -0.71
    POSITIVE LOGITS
     generations
    1.13
     days
    0.99
     attractions
    0.99
     weeks
    0.96
     seasons
    0.92
     administrations
    0.91
     months
    0.88
     chapters
    0.85
     generation
    0.84
     arrivals
    0.83
    Activations Density 0.070%

    No Known Activations