© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1983
    Prev
    Next
    INDEX
    Explanations

    code related to database queries, specifically the find operation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.16
    0.7%
    756
    +0.11
    0.5%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.02
    586
    +0.11
    0.02
    255
    +0.11
    0.02
    Negative Logits
     incorpor
    -0.72
    chwitz
    -0.66
    zan
    -0.65
     reconc
    -0.64
     mathemat
    -0.62
    spread
    -0.62
     oun
    -0.60
    upuncture
    -0.60
    punk
    -0.59
    involved
    -0.59
    POSITIVE LOGITS
     });
    1.86
     })
    1.78
     }
    1.70
     };
    1.53
     },
    1.51
     }}
    1.47
    });
    1.41
    })
    1.35
    }
    1.31
    };
    1.30
    Activations Density 0.061%

    No Known Activations