© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18827
    Prev
    Next
    INDEX
    Explanations

    political news events and interactions

    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
    430
    +0.17
    0.8%
    564
    +0.11
    0.5%
    585
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.17
    0.09
    114
    +0.11
    0.05
    132
    +0.10
    0.05
    Negative Logits
     };
    -0.68
    }}}
    -0.66
     2020
    -0.64
     },
    -0.64
     nutshell
    -0.60
    }\
    -0.60
    }}
    -0.60
     Matter
    -0.58
     CMS
    -0.56
     fundament
    -0.54
    POSITIVE LOGITS
     sidx
    0.92
    essage
    0.81
     advocating
    0.75
    assador
    0.74
    agree
    0.71
    ilitary
    0.70
    successfully
    0.69
     agreeing
    0.69
     proposing
    0.69
     complaining
    0.69
    Activations Density 0.495%

    No Known Activations