Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 1814
    Prev
    Next
    INDEX
    Explanations

    numerical references in dates and citations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    +0.12
    0.6%
    559
    +0.10
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.12
    0.05
    472
    +0.10
    0.05
    6
    +0.09
    0.05
    Negative Logits
    agra
    -0.65
    gone
    -0.62
    sels
    -0.59
     hog
    -0.58
    liga
    -0.57
     illiter
    -0.57
     imperson
    -0.57
     pressures
    -0.57
     laure
    -0.56
     unpre
    -0.56
    POSITIVE LOGITS
    ]).
    1.28
    ][
    1.23
    ]
    1.21
    ],[
    1.21
    ]),
    1.14
    ].
    1.13
    ]"
    1.13
    ])
    1.12
    ]);
    1.07
    ]:
    1.03
    Activations Density 0.144%

    No Known Activations