© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 1536
    9. 8-RES_FS1536-JB
    11. 1124
    Prev
    Next
    INDEX
    Explanations

    dates in historical contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    475
    +0.11
    0.5%
    472
    +0.10
    0.5%
    559
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.11
    0.06
    6
    +0.10
    0.07
    475
    +0.10
    0.06
    Negative Logits
    agra
    -0.70
    gone
    -0.66
    yre
    -0.60
    pass
    -0.57
     laure
    -0.56
    aye
    -0.56
     pressures
    -0.55
     Polk
    -0.55
     hog
    -0.55
    geries
    -0.55
    POSITIVE LOGITS
    ]).
    1.23
    ],[
    1.21
    ]
    1.19
    ][
    1.14
    ]),
    1.11
    ].
    1.10
    ])
    1.08
    ]"
    1.07
    ]:
    1.02
    ]);
    0.99
    Activations Density 0.862%

    No Known Activations