© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4659
    Prev
    Next
    INDEX
    Explanations

    references to geographical or political contexts

    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
    300
    +0.11
    0.5%
    82
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.11
    0.07
    39
    +0.11
    0.07
    575
    +0.10
    0.08
    Negative Logits
     concess
    -0.67
     informational
    -0.59
     paraph
    -0.56
     Debor
    -0.55
     Anth
    -0.55
     proverb
    -0.55
     unden
    -0.54
     reciprocal
    -0.53
     condol
    -0.52
    wolves
    -0.52
    POSITIVE LOGITS
    )),
    1.06
    ))
    1.01
    ));
    0.98
    ]),
    0.94
    )—
    0.91
     )))
    0.91
    )?
    0.90
    ),
    0.87
     ))
    0.87
    )))
    0.84
    Activations Density 0.710%

    No Known Activations