© 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. 4863
    Prev
    Next
    INDEX
    Explanations

    rankings or numerical positions in lists or polls

    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
    373
    +0.17
    0.8%
    152
    +0.10
    0.5%
    386
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.17
    0.03
    241
    +0.10
    0.03
    376
    +0.09
    0.03
    Negative Logits
     Observatory
    -0.62
    lectic
    -0.59
     dism
    -0.59
    metry
    -0.57
     conversions
    -0.56
     arrivals
    -0.55
    avascript
    -0.54
    atories
    -0.54
     extraction
    -0.54
    RECT
    -0.53
    POSITIVE LOGITS
    rix
    0.65
    EMBER
    0.65
    pine
    0.65
    afety
    0.64
    advertisement
    0.63
    ½
    0.63
     Tens
    0.61
    vu
    0.61
    outheastern
    0.60
    trust
    0.60
    Activations Density 0.113%

    No Known Activations