© 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. 5654
    Prev
    Next
    INDEX
    Explanations

    instances of coding constructs and data types in programming languages

    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
    +0.12
    0.5%
    160
    +0.11
    0.5%
    303
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.12
    0.03
    442
    +0.11
    0.02
    640
    +0.10
    0.02
    Negative Logits
     Hundred
    -0.66
     enriched
    -0.63
     mounts
    -0.59
     compressed
    -0.59
     Sharing
    -0.58
     squats
    -0.58
    hai
    -0.56
     Arche
    -0.56
     Patriarch
    -0.56
     Zar
    -0.55
    POSITIVE LOGITS
    }
    1.25
    });
    1.22
     });
    1.09
    }\
    1.08
    };
    1.05
    .}
    0.99
    }:
    0.99
     }
    0.95
    }"
    0.93
    /*
    0.92
    Activations Density 0.046%

    No Known Activations